SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2210.11035 · NeurIPS · 2022

PointTAD: Multi-Label Temporal Action Detection with Learnable Query Points

Limin Wang, Jing Tan, Xiaotong Zhao, Xintian Shi, Bin Kang

arXiv · PDF · Open in the Atlas

Code that ran

6 of 8 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (1 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 5 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/2210.11035.json · badge: /api/ran/2210.11035.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
PeizeSun/SparseR-CNN canonical (classifier label)
classifier basis not recorded on the link
5 ran · 2 no recorded run
mcg-nju/pointtad community
Papers with Code archive
1 ran · 0 no recorded run
FunctionStatusWhere it lives
PointTAD Ran
ran on a synthesized input · constructed an object; no result was computed
mcg-nju/pointtad/models/pointtad.py
code served (permissive licence) · get_code("17bf002b5ad9eee4")
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 an instance of its own class, PointTAD: the run constructed the object and did not call it, so no result was computed. 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)

# Define a minimal backbone that matches the expected interface
class MinimalBackbone(nn.Module):
    def __init__(self):
        super().__init__()
        self.outdim_5c = 8
        self.outdim_4f = 6
        # Dummy conv layers to produce the expected feature maps
        self.conv_5c = nn.Conv3d(3, self.outdim_5c, kernel_size=3, padding=1)
        self.conv_4f = nn.Conv3d(3, self.outdim_4f, kernel_size=3, padding=1)
    
    def forward(self, x):
        # x shape: (batch_size, 3, T, H, W)
        feat_5c = self.conv_5c(x)  # (bs, 8, T, H, W)
        feat_4f = self.conv_4f(x)  # (bs, 6, T, H, W)
        return {
            'Mixed_5c': feat_5c,
            'Mixed_4f': feat_4f
        }

# Define a minimal decoder that matches the expected interface
class MinimalDecoder(nn.Module):
    def __init__(self, hidden_dim, num_queries, num_classes, num_querypoints):
        super().__init__()
        self.hidden_dim = hidden_dim
        self.num_queries = num_queries
        self.num_classes = num_classes
        self.num_querypoints = num_querypoints
        # Dummy output layers
        self.class_pred = nn.Linear(hidden_dim, num_classes + 1)
        self.coord_pred = nn.Linear(hidden_dim, num_querypoints)
    
    def forward(self, features, proposal_points, init_proposal_features):
        # features: (bs, window_size, hidden_dim)
        # proposal_points: (bs, num_queries, num_querypoints)
        # init_proposal_features: (num_queries, hidden_dim)
        
        bs = features.shape[0]
        
        # Aggregate features for class and coordinate predictions
        feat_agg = features.mean(dim=1, keepdim=True)  # (bs, 1, hidden_dim)
        
        # Predict class logits for all queries
        outputs_class = [self.class_pred(feat_agg.expand(bs, self.num_queries, -1))]  # List of (bs, num_queries, num_classes+1)
        
        # Predict segments (coordinates)
        outputs_coord = [self.coord_pred(feat_agg.expand(bs, self.num_queries, -1))]  # List of (bs, num_queries, num_querypoints)
        
        # Hidden states
        hs = feat_agg.expand(bs, self.num_queries, -1)  # (bs, num_queries, hidden_dim)
        
        return outputs_class, outputs_coord, hs

# Construct arguments
backbone = MinimalBackbone()
decoder = MinimalDecoder(hidden_dim=4, num_queries=3, num_classes=5, num_querypoints=2)

ARGS = {
    'backbone': backbone,
    'decoder': decoder,
    'hidden_dim': 4,
    'num_classes': 5,
    'window_size': 8,
    'num_queries': 3,
    'num_querypoints': 2,
    'aux_loss': 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 PointTAD — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a PointTAD 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
batched_nms Ran
ran; our contract draft was wrong, not the code
PeizeSun/SparseR-CNN/detectron2/layers/nms.py
pointer only (licence: MIT); the stored copy get_code serves, from mxin262/swintextspotter, is pointer only (licence: NONE) · get_code("5a3c7069b28e9ffb")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from mxin262/swintextspotter, 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.

convert_basic_c2_names Ran
ran; our contract draft was wrong, not the code
PeizeSun/SparseR-CNN/detectron2/checkpoint/c2_model_loading.py
code served (permissive licence) · get_code("e8526a516b4f9206")
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 copy
import re

# Analyze the function: it takes a list of strings (original_keys) and applies
# various string transformations to them. It doesn't use any complex objects,
# just list operations and string manipulations.

ARGS = {
    'original_keys': [
        'pred_b',
        'pred_w',
        'conv_b',
        'conv_w',
        'bn_s',
        'bn_bias',
        'bn_rm',
        'bn_riv',
        'bn_gamma',
        'bn_beta',
        'gn_s',
        'gn_bias',
        'res_conv1_norm_weight',
        'conv1_weight',
        'layer_branch1_weight',
        'layer_branch2a_bias',
        'layer_branch2b_weight',
        'layer_branch2c_bias',
        'body_conv_fcn_weight',
        'AnnIndex_lowres',
        'Index_UV_lowres',
        'U_lowres',
        'V_lowres',
    ]
}
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 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
convert_c2_detectron_names Ran
ran; our contract draft was wrong, not the code
PeizeSun/SparseR-CNN/detectron2/checkpoint/c2_model_loading.py
code served (permissive licence) · get_code("52810b504f0d1066")
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 torch
import logging
import copy

torch.manual_seed(0)

# Set up logging to avoid issues
logging.basicConfig(level=logging.INFO)

# Create a minimal weights dict with C2-style naming conventions
# The function processes weight names, so we just need dummy tensors
weights = {
    'res_conv1_bn_s': torch.randn(4),
    'res_conv1_bn_bias': torch.randn(4),
    'pred_w': torch.randn(3, 4),
    'pred_b': torch.randn(3),
    'conv_rpn_fpn2_weight': torch.randn(4, 4),
    'rpn_bbox_pred_weight': torch.randn(4, 4),
    'rpn_cls_logits_weight': torch.randn(4, 4),
    'fc6_weight': torch.randn(4, 4),
    'fc7_bias': torch.randn(4),
    'fpn_inner_res2_2_sum_lateral_weight': torch.randn(4, 4),
    'fpn_res2_2_sum_weight': torch.randn(4, 4),
    'fpn_inner_res3_3_sum_lateral_bias': torch.randn(4),
    'fpn_res3_3_sum_bias': torch.randn(4),
    'bbox_pred_weight': torch.randn(4, 4),
    'cls_score_bias': torch.randn(4),
    'head_conv_weight': torch.randn(4, 4),
}

ARGS = {
    'weights': weights,
}
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 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
pad_masks Ran
ran; our contract draft was wrong, not the code
PeizeSun/SparseR-CNN/detectron2/layers/mask_ops.py
pointer only (licence: MIT); the stored copy get_code serves, from thinklab-sjtu/bench2drivezoo, is pointer only (licence: NOASSERTION) · get_code("406f84cf799ed34d")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from thinklab-sjtu/bench2drivezoo, 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.

paste_mask_in_image_old Ran
ran; our contract draft was wrong, not the code
PeizeSun/SparseR-CNN/detectron2/layers/mask_ops.py
pointer only (licence: MIT); the stored copy get_code serves, from thinklab-sjtu/bench2drivezoo, is pointer only (licence: NOASSERTION) · get_code("d03592674030077f")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from thinklab-sjtu/bench2drivezoo, 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.

batched_nms_rotated Not yet run
unverified (harvested, no recorded run)
PeizeSun/SparseR-CNN/detectron2/layers/nms.py
code served (permissive licence) · get_code("af6fcdbdb551e018")
How it ran

no invocation recorded.

nms_rotated Not yet run
unverified (harvested, no recorded run)
PeizeSun/SparseR-CNN/detectron2/layers/nms.py
code served (permissive licence) · get_code("d3fa37a000ad294d")
How it ran

no invocation recorded.

Also present in other papers' code

Of 8 samples lifted from this paper's linked repositories, 8 carry a function identity and 0 do not. Of the 8 distinct functions with an identity, 7 are also present in other papers whose code we hold (5 with at least one paper dated earlier, 0 the same month, 7 later) and 1 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
convert_basic_c2_names 45 other papers
19 dated earlier, 23 later, 3 same year, order not determinable
1703.06870 (2017-03)
Mask R-CNN
1804.08864 (2018-04)
Learning to See the Invisible: End-to-End Trainable Amodal Instance Segmentation
1901.08164 (2019-01)
Decoupled Greedy Learning of CNNs
and 42 more not named here
convert_c2_detectron_names 29 other papers
18 dated earlier, 9 later, 2 same year, order not determinable
1703.06870 (2017-03)
Mask R-CNN
1804.08864 (2018-04)
Learning to See the Invisible: End-to-End Trainable Amodal Instance Segmentation
1901.08164 (2019-01)
Decoupled Greedy Learning of CNNs
and 26 more not named here
pad_masks 22 other papers
11 dated earlier, 9 later, 2 same year, order not determinable
1703.06870 (2017-03)
Mask R-CNN
1804.08864 (2018-04)
Learning to See the Invisible: End-to-End Trainable Amodal Instance Segmentation
1908.07836 (2019-08)
PubLayNet: largest dataset ever for document layout analysis
and 19 more not named here
paste_mask_in_image_old 22 other papers
11 dated earlier, 9 later, 2 same year, order not determinable
1703.06870 (2017-03)
Mask R-CNN
1804.08864 (2018-04)
Learning to See the Invisible: End-to-End Trainable Amodal Instance Segmentation
1908.07836 (2019-08)
PubLayNet: largest dataset ever for document layout analysis
and 19 more not named here
nms_rotated 14 other papers
9 dated earlier, 3 later, 2 same year, order not determinable
1703.06870 (2017-03)
Mask R-CNN
1804.08864 (2018-04)
Learning to See the Invisible: End-to-End Trainable Amodal Instance Segmentation
1908.07836 (2019-08)
PubLayNet: largest dataset ever for document layout analysis
and 11 more not named here
batched_nms_rotated 4 other papers
4 later
2304.03752 (2023-04)
V3Det: Vast Vocabulary Visual Detection Dataset
2307.13619 (2023-07)
RecursiveDet: End-to-End Region-based Recursive Object Detection
2403.10191 (2024-03)
Generative Region-Language Pretraining for Open-Ended Object Detection
and 1 more not named here
batched_nms 2 other papers
2 later
2307.13619 (2023-07)
RecursiveDet: End-to-End Region-based Recursive Object Detection
2404.04624 (2024-04)
Bridging the Gap Between End-to-End and Two-Step Text Spotting

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

Traditional temporal action detection (TAD) usually handles untrimmed videos with small number of action instances from a single label (e.g., ActivityNet, THU-MOS). However, this setting might be unrealistic as different classes of actions often co-occur in practice. In this paper, we focus on the task of multi-label temporal action detection that aims to localize all action instances from a multi-label untrimmed video. Multi-label TAD is more challenging as it requires for finegrained class discrimination within a single video and precise localization of the co-occurring instances. To mitigate this issue, we extend the sparse query-based detection paradigm from the traditional TAD and propose the multi-label TAD framework of PointTAD. Specifically, our PointTAD introduces a small set of learnable query points to represent the important frames of each action instance. This point-based representation provides a flexible mechanism to localize the discriminative frames at boundaries and as well the important frames inside the action. Moreover, we perform the action decoding process with the Multi-level Interactive Module to capture both point-level and instance-level action semantics. Finally, our PointTAD employs an end-to-end trainable framework simply based on RGB input for easy deployment. We evaluate our proposed method on two popular benchmarks and introduce the new metric of detection-mAP for multi-label TAD. Our model outperforms all previous methods by a large margin under the detection-mAP metric, and also achieves promising results under the segmentation-mAP metric. Code is available at https://github.com/MCG-NJU/PointTAD.

For agents

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

get_harvested_code_for_paper("2210.11035")
get_code_for_paper("2210.11035")
have("2210.11035")

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

curl https://syntology.ai/api/ran/2210.11035.json

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

[![Syntology run record](https://syntology.ai/api/ran/2210.11035.svg)](https://syntology.ai/paper/2210.11035)

Connect an agent — have() is free.