SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2303.04995 · CVPR · 2023

Text-Visual Prompting for Efficient 2D Temporal Video Grounding

Xin Chen, Sijia Liu, Ke Ding, Yimeng Zhang, Jinghan Jia

arXiv · PDF · Open in the Atlas

Code that ran

14 of 16 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 0 violated it and 7 have no contract verdict; 6 failures of our instrument; 2 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2303.04995.json · badge: /api/ran/2303.04995.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
intel/TVP canonical (classifier label)
classifier basis not recorded on the link
14 ran · 2 no recorded run
FunctionStatusWhere it lives
conv3x3 Ran
ran on a synthesized input
intel/TVP/src/modeling/grid_feat.py
code served (permissive licence) · get_code("17e89eef72e37efe")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Conv2d. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
from torch import nn

torch.manual_seed(0)

ARGS = {
    'in_planes': 3,
    'out_planes': 64,
    'stride': 1,
    'groups': 1,
    'dilation': 1,
    'init_identity': False,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Conv2d — a Conv2d output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Conv2d output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
dis_iou_loss Ran
ran on a synthesized input
intel/TVP/src/modeling/modeling.py
code served (permissive licence) · get_code("9397957c09ba96d3")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 1, dtype family float, shape (2,) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# Create sample tensors for candidates and ground truth
# candidates: shape (batch_size, 2) with [start, end] positions
# gt: shape (batch_size, 2) with [start, end] positions
candidates = torch.tensor([
    [1.0, 5.0],
    [2.0, 6.0]
], dtype=torch.int64)

gt = torch.tensor([
    [1.5, 4.5],
    [2.5, 5.5]
], dtype=torch.int64)

ARGS = {
    "candidates": candidates,
    "gt": gt
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 1, dtype family float, shape (2,) — shape (2,) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_padding Ran
ran; our contract draft was wrong, not the code
intel/TVP/src/datasets/data_utils.py
code served (permissive licence) · get_code("0cf387da46369b1a")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned tuple, ndim 1, dtype family int; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
from PIL import Image
import numpy as np

torch.manual_seed(0)

# Test case 1: torch.Tensor input with pad_all=False
tensor_image = torch.randn(1, 3, 4, 5)  # batch=1, channels=3, h=4, w=5

# Test case 2: PIL Image input with pad_all=True
pil_image = Image.new('RGB', (6, 7))  # w=6, h=7

ARGS = {
    "image": tensor_image,
    "max_w": 10,
    "max_h": 12,
    "pad_all": False
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 1, dtype family int — a tuple output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_random_sample_indices Ran
ran on a synthesized input
intel/TVP/src/modeling/modeling.py
code served (permissive licence) · get_code("f31be4ddaa3ec6c2")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 1, dtype family int, shape (10,) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np
import torch

torch.manual_seed(0)

ARGS = {
    'seq_len': 50,
    'num_samples': 10,
    'device': torch.device('cpu')
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 1, dtype family int, shape (10,) — shape (10,) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_start_end_idx Ran
ran, honoured the contract we drafted
intel/TVP/src/datasets/decoder.py
code served (permissive licence) · get_code("707f6cd75833c65d")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned tuple, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import random

random.seed(0)

ARGS = {
    "video_size": 100,
    "clip_size": 16,
    "clip_idx": -1,
    "num_clips": 4,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 1, dtype family float — a tuple output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_video_decoding_kwargs Ran
ran on a synthesized input
intel/TVP/src/datasets/dataset_base.py
code served (permissive licence) · get_code("b6331823c359e9d8")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned dict. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# A simple container object that mimics a video container
class VideoContainer:
    def __init__(self):
        self.duration = 10.0
        self.fps = 30

# Test case 1: num_clips is None, sampling_strategy is 'rand'
ARGS = {
    'container': VideoContainer(),
    'num_frames': 8,
    'target_fps': 24,
    'num_clips': None,
    'clip_idx': None,
    'sampling_strategy': 'rand',
    'safeguard_duration': False,
    'video_max_pts': None
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
image_to_tensor Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
intel/TVP/src/datasets/data_utils.py
code served (permissive licence) · get_code("e9242c50098a6ea2")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 3, dtype family float, shape (3, 5, 7) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import numpy as np

torch.manual_seed(0)

# Test case 1: 3D image (H, W, C)
image_3d = np.random.rand(5, 7, 3).astype(np.float32)

# Test case 2: 2D image (H, W)
image_2d = np.random.rand(5, 7).astype(np.float32)

# Test case 3: 4D batch (B, H, W, C)
image_4d = np.random.rand(2, 5, 7, 3).astype(np.float32)

# Using the 3D case as primary example
ARGS = {
    'image': image_3d,
    'keepdim': True
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 3, dtype family float, shape (3, 5, 7) — shape (3, 5, 7) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
instance_bce_with_logits Ran
ran on a synthesized input
intel/TVP/src/modeling/modeling.py
code served (permissive licence) · get_code("5a4d93d8be97ccd9")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn.functional as F

torch.manual_seed(0)

# The function expects:
# - logits: 2D tensor of shape (batch_size, num_instances)
# - labels: 2D tensor of shape (batch_size, num_instances) with binary values
# - reduction: string, either 'mean' or 'none'

batch_size = 2
num_instances = 4

logits = torch.randn(batch_size, num_instances)
labels = torch.randint(0, 2, (batch_size, num_instances)).float()
reduction = 'mean'

ARGS = {
    'logits': logits,
    'labels': labels,
    'reduction': reduction
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 0, dtype family float, shape () — shape () as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
load_decompress_img_from_lmdb_value Ran
ran on a synthesized input
intel/TVP/src/datasets/dataset_base.py
code served (permissive licence) · get_code("daa2b8808499576a")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned PngImageFile. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import io
from PIL import Image
import numpy as np

# Create a small valid PNG image in memory
# This creates a minimal 2x2 RGB image
img_array = np.uint8(np.random.randint(0, 256, (2, 2, 3)))
pil_img = Image.fromarray(img_array, mode='RGB')

# Save the PIL image to a bytes buffer
buffer = io.BytesIO()
pil_img.save(buffer, format='PNG')
lmdb_value = buffer.getvalue()

ARGS = {
    "lmdb_value": lmdb_value
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type PngImageFile — a PngImageFile output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a PngImageFile output the recorded ndim 3 and dtype family int describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
mask_batch_text_tokens Ran
ran; our contract draft was wrong, not the code
intel/TVP/src/datasets/data_utils.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from microsoft/xpretrain, is pointer only (licence: NOASSERTION) · get_code("f828f173e6c2fea2")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from microsoft/xpretrain, and GitHub could not classify the licence of that repository (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

mish Ran
ran; our contract draft was wrong, not the code
intel/TVP/src/modeling/transformers.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from llyx97/sparse-and-robust-PLM, is pointer only (licence: NONE) · get_code("060527bb34794b59")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from llyx97/sparse-and-robust-PLM, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

move_to_cuda Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
intel/TVP/src/datasets/dataloader.py
code served (permissive licence) · get_code("b68769dd52ad6c44")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned dict. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# The function move_to_cuda accepts a single parameter: batch
# It can be a Tensor, list, tuple, dict, or other type
# We'll test with a complex nested structure to cover all branches

batch = {
    "tensor_field": torch.randn(2, 4),
    "list_field": [torch.randn(2, 3), torch.randn(1, 4)],
    "tuple_field": (torch.randn(2, 2), torch.randn(3, 4)),
    "nested_dict": {
        "inner_tensor": torch.randn(2, 5),
        "inner_list": [torch.randn(1, 2)]
    },
    "scalar_field": 42,
    "string_field": "test"
}

ARGS = {
    "batch": batch
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
parse_with_config Ran
ran; our contract draft was wrong, not the code
intel/TVP/src/configs/config.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from SixCorePeach/MCAM, is pointer only (licence: NONE) · get_code("3e81145412a40e36")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from SixCorePeach/MCAM, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

temporal_sampling Ran
ran on a synthesized input
intel/TVP/src/datasets/decoder.py
code served (permissive licence) · get_code("f307b4793e8204b7")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned list, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import numpy as np

torch.manual_seed(0)

# Create a stand-in for av.video.frame.VideoFrame
class MockVideoFrame:
    def __init__(self, frame_id):
        self.frame_id = frame_id
    
    def __repr__(self):
        return f"MockVideoFrame({self.frame_id})"

# Create a list of mock video frames
frames = [MockVideoFrame(i) for i in range(10)]

# Define arguments
ARGS = {
    "frames": frames,
    "start_idx": 0,
    "end_idx": 9,
    "num_samples": 5
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 1, dtype family float — a list output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
load_tf_weights_in_bert Not yet run
unverified (harvested, no recorded run)
intel/TVP/src/modeling/transformers.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from llyx97/sparse-and-robust-PLM, is pointer only (licence: NONE) · get_code("0766f48ad6e01b56")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from llyx97/sparse-and-robust-PLM, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

pyav_decode_stream Not yet run
unverified (harvested, no recorded run)
intel/TVP/src/datasets/decoder.py
code served (permissive licence) · get_code("b28b46ef7776c434")
How it ran

no invocation recorded.

Also present in other papers' code

Of 16 samples lifted from this paper's linked repositories, 16 carry a function identity and 0 do not. Of the 16 distinct functions with an identity, 14 are also present in other papers whose code we hold (14 with at least one paper dated earlier, 1 the same month, 7 later) and 2 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
mish 19 other papers
13 dated earlier, 6 later
2006.04884 (2020-06)
On the Stability of Fine-tuning BERT: Misconceptions, Explanations, and Strong Baselines
2007.12223 (2020-07)
The Lottery Ticket Hypothesis for Pre-trained BERT Networks
2012.07463 (2020-12)
Parameter-Efficient Transfer Learning with Diff Pruning
and 16 more not named here
load_tf_weights_in_bert 16 other papers
11 dated earlier, 5 later
2006.04884 (2020-06)
On the Stability of Fine-tuning BERT: Misconceptions, Explanations, and Strong Baselines
2007.12223 (2020-07)
The Lottery Ticket Hypothesis for Pre-trained BERT Networks
2012.07463 (2020-12)
Parameter-Efficient Transfer Learning with Diff Pruning
and 13 more not named here
parse_with_config 6 other papers
3 dated earlier, 1 the same month, 2 later
Li_Align_and_Prompt_Video-and-Language_Pre-Training_With_Entity_Prompts_CVPR_2022_paper (2022 (year only))
Align and Prompt: Video-and-Language Pre-training with Entity Prompts
Lin_SwinBERT_End-to-End_Transformers_With_Sparse_Attention_for_Video_Captioning_CVPR_2022_paper (2022 (year only))
SWINBERT: End-to-End Transformers with Sparse Attention for Video Captioning
2206.03428 (2022-06)
Revealing Single Frame Bias for Video-and-Language Learning
and 3 more not named here
mask_batch_text_tokens 5 other papers
3 dated earlier, 2 later
Li_Align_and_Prompt_Video-and-Language_Pre-Training_With_Entity_Prompts_CVPR_2022_paper (2022 (year only))
Align and Prompt: Video-and-Language Pre-training with Entity Prompts
2206.03428 (2022-06)
Revealing Single Frame Bias for Video-and-Language Learning
2210.06031 (2022-10)
Long-Form Video-Language Pre-Training with Multimodal Temporal Contrastive Learning
and 2 more not named here
image_to_tensor 4 other papers
2 dated earlier, 2 later
Li_Align_and_Prompt_Video-and-Language_Pre-Training_With_Entity_Prompts_CVPR_2022_paper (2022 (year only))
Align and Prompt: Video-and-Language Pre-training with Entity Prompts
2206.03428 (2022-06)
Revealing Single Frame Bias for Video-and-Language Learning
2407.12338 (2024-07)
GUME: Graphs and User Modalities Enhancement for Long-Tail Multimodal Recommendation
and 1 more not named here
pyav_decode_stream 4 other papers
4 dated earlier
2005.03788 (2020-05)
ProSelfLC: Progressive Self Label Correction for Training Robust Deep Neural Networks
136950157 (2022 (year only))
K-centered Patch Sampling for Efficient Video Recognition
and 1 more not named here
get_start_end_idx 3 other papers
3 dated earlier
2005.03788 (2020-05)
ProSelfLC: Progressive Self Label Correction for Training Robust Deep Neural Networks
136640364 (2022 (year only))
Continual 3D Convolutional Neural Networks for Real-time Processing of Videos
2206.03428 (2022-06)
Revealing Single Frame Bias for Video-and-Language Learning
move_to_cuda 3 other papers
2 dated earlier, 1 later
Li_Align_and_Prompt_Video-and-Language_Pre-Training_With_Entity_Prompts_CVPR_2022_paper (2022 (year only))
Align and Prompt: Video-and-Language Pre-training with Entity Prompts
2206.03428 (2022-06)
Revealing Single Frame Bias for Video-and-Language Learning
2409.19865 (2024-09)
TokenBinder: Text-Video Retrieval with One-to-Many Alignment Paradigm
get_padding 2 other papers
1 dated earlier, 1 later
2206.03428 (2022-06)
Revealing Single Frame Bias for Video-and-Language Learning
2409.19865 (2024-09)
TokenBinder: Text-Video Retrieval with One-to-Many Alignment Paradigm
instance_bce_with_logits 2 other papers
2 dated earlier
2108.04024 (2021-08)
Image Retrieval on Real-life Images with Pre-trained Vision-and-Language Models
2206.03428 (2022-06)
Revealing Single Frame Bias for Video-and-Language Learning
conv3x3 1 other paper
1 dated earlier
2206.03428 (2022-06)
Revealing Single Frame Bias for Video-and-Language Learning
get_random_sample_indices 1 other paper
1 dated earlier
2206.03428 (2022-06)
Revealing Single Frame Bias for Video-and-Language Learning
get_video_decoding_kwargs 1 other paper
1 dated earlier
2206.03428 (2022-06)
Revealing Single Frame Bias for Video-and-Language Learning
temporal_sampling 1 other paper
1 dated earlier
2206.03428 (2022-06)
Revealing Single Frame Bias for Video-and-Language Learning

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

In this paper, we study the problem of temporal video grounding (TVG), which aims to predict the starting/ending time points of moments described by a text sentence within a long untrimmed video. Benefiting from fine-grained 3D visual features, the TVG techniques have achieved remarkable progress in recent years. However, the high complexity of 3D convolutional neural networks (CNNs) makes extracting dense 3D visual features time-consuming, which calls for intensive memory and computing resources. Towards efficient TVG, we propose a novel text-visual prompting (TVP) framework, which incorporates optimized perturbation patterns (that we call 'prompts') into both visual inputs and textual features of a TVG model. In sharp contrast to 3D CNNs, we show that TVP allows us to effectively co-train vision encoder and language encoder in a 2D TVG model and improves the performance of crossmodal feature fusion using only low-complexity sparse 2D visual features. Further, we propose a Temporal-Distance IoU (TDIoU) loss for efficient learning of TVG. Experiments on two benchmark datasets, Charades-STA and Ac-tivityNet Captions datasets, empirically show that the proposed TVP significantly boosts the performance of 2D TVG (e.g., 9.79% improvement on Charades-STA and 30.77% improvement on ActivityNet Captions) and achieves 5× inference acceleration over TVG using 3D visual features. Codes are available at Open.Intel.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2303.04995")
get_code_for_paper("2303.04995")
have("2303.04995")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2303.04995.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2303.04995.svg)](https://syntology.ai/paper/2303.04995)

Connect an agent — have() is free.