SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2403.12042 · ECCV · 2024

Exploring Pre-trained Text-to-Video Diffusion Models for Referring Video Object Segmentation

Dongdong Chen, Junsong Yuan, Zixin Zhu, Xuelu Feng, Chunming Qiao, Gang Hua

arXiv · PDF · Open in the Atlas

Code that ran

16 of 20 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (5 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; 8 failures of our instrument; 4 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/2403.12042.json · badge: /api/ran/2403.12042.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
buxiangzhiren/vd-it canonical (classifier label)
classifier basis: plan_row
7 ran · 2 no recorded run
buxiangzhiren/VD-IT community
Papers with Code archive
9 ran · 2 no recorded run
FunctionStatusWhere it lives
FeatureResizer Ran
ran on a synthesized input · constructed an object; no result was computed
buxiangzhiren/VD-IT/models/diffvos_cross.py
pointer only (licence: NOASSERTION) · get_code("6698eb19524677b2")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, buxiangzhiren/VD-IT (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.

LFMResizeAdaptive Ran
ran on a synthesized input
buxiangzhiren/VD-IT/models/diffvos_cross.py
pointer only (licence: NOASSERTION) · get_code("4c35fc550aefb115")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, buxiangzhiren/VD-IT (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.

MSO Ran
ran on a synthesized input · constructed an object; no result was computed
buxiangzhiren/VD-IT/models/diffvos_cross.py
pointer only (licence: NOASSERTION) · get_code("1a0f5b3fe60cf400")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, buxiangzhiren/VD-IT (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.

NestedTensor Ran
ran on a synthesized input · constructed an object; no result was computed
buxiangzhiren/VD-IT/models/diffvos_cross.py
pointer only (licence: NOASSERTION) · get_code("04e2b0ca4fcbb7b1")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, buxiangzhiren/VD-IT (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.

PositionEmbeddingSine1D Ran
ran on a synthesized input · constructed an object; no result was computed
buxiangzhiren/VD-IT/models/diffvos_cross.py
pointer only (licence: NOASSERTION) · get_code("78874d632c11fd54")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, buxiangzhiren/VD-IT (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.

TextEncoder Ran
ran on a synthesized input · constructed an object; no result was computed
buxiangzhiren/VD-IT/models/diffvos_cross.py
pointer only (licence: NOASSERTION) · get_code("f0fa25effadd804b")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, buxiangzhiren/VD-IT (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.

VisionLanguageFusionModule Ran
ran on a synthesized input
buxiangzhiren/VD-IT/models/diffvos_cross.py
pointer only (licence: NOASSERTION) · get_code("b87df838cef10bb6")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, buxiangzhiren/VD-IT (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.

_get_src_permutation_idx Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
buxiangzhiren/VD-IT/models/diffvos_cross.py
pointer only (licence: NOASSERTION) · get_code("d243b7d81e036269")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, buxiangzhiren/VD-IT (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.

aligned_bilinear Ran
ran; our contract draft was wrong, not the code
buxiangzhiren/vd-it/models/diffvos_cross.py
pointer only (licence: NONE) · get_code("29dbbaafa4be18e1")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, buxiangzhiren/vd-it 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.

box_cxcywh_to_xyxy Ran
ran; our contract draft was wrong, not the code
buxiangzhiren/vd-it/inference_davis.py
pointer only (licence: NONE); the stored copy get_code serves, from ut-vision/ActionVOS, is pointer only (licence: NONE) · get_code("ef1a3e10a9dbf4a9")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, buxiangzhiren/vd-it 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.

compute_locations Ran
ran, honoured the contract we drafted
buxiangzhiren/vd-it/models/diffvos_cross.py
pointer only (licence: NONE); the stored copy get_code serves, from bo-miao/refhuman, is pointer only (licence: NONE) · get_code("ed1a308adb65f645")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, buxiangzhiren/vd-it 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.

get_window_size Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
buxiangzhiren/vd-it/models/itcross_video_swin_transformer.py
pointer only (licence: NONE); the stored copy get_code serves, from shiqiyu/opengait, is pointer only (licence: NONE) · get_code("aad0ea11cb13d353")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, buxiangzhiren/vd-it 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.

nested_tensor_from_videos_list Ran
ran; our contract draft was wrong, not the code
buxiangzhiren/VD-IT/models/diffvos_cross.py
pointer only (licence: NOASSERTION) · get_code("0ac81da8baf234ef")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, buxiangzhiren/VD-IT (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.

rescale_bboxes Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
buxiangzhiren/vd-it/inference_davis.py
pointer only (licence: NONE); the stored copy get_code serves, from ut-vision/ActionVOS, is pointer only (licence: NONE) · get_code("2626a807bce7587a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, buxiangzhiren/vd-it 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.

window_partition Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
buxiangzhiren/vd-it/models/itcross_video_swin_transformer.py
pointer only (licence: NONE); the stored copy get_code serves, from pkyong95/PCVOS, is pointer only (licence: GPL-3.0) · get_code("4876d8faacbd6927")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, buxiangzhiren/vd-it 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.

window_reverse Ran
ran; our contract draft was wrong, not the code
buxiangzhiren/vd-it/models/itcross_video_swin_transformer.py
pointer only (licence: NONE); the stored copy get_code serves, from tony890048/exPreCast, is pointer only (licence: NONE) · get_code("75fd6fbfca7a246c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, buxiangzhiren/vd-it 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.

RobertaTokenizer Not yet run
unverified (harvested, no recorded run)
buxiangzhiren/VD-IT/models/diffvos_cross.py
pointer only (licence: NOASSERTION) · get_code("98678812f22a7806")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, buxiangzhiren/VD-IT (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. No invocation recorded.

VDIT Not yet run
unverified (harvested, no recorded run)
buxiangzhiren/VD-IT/models/diffvos_cross.py
pointer only (licence: NOASSERTION) · get_code("1e4b5e6aa312128e")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, buxiangzhiren/VD-IT (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. No invocation recorded.

parse_dynamic_params Not yet run
unverified (harvested, no recorded run)
buxiangzhiren/vd-it/models/diffvos_cross.py
pointer only (licence: NONE); the stored copy get_code serves, from bo-miao/refhuman, is pointer only (licence: NONE) · get_code("af3dd7f95037a80f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, buxiangzhiren/vd-it 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.

vis_add_mask Not yet run
unverified (harvested, no recorded run)
buxiangzhiren/vd-it/inference_davis.py
pointer only (licence: NONE); the stored copy get_code serves, from ut-vision/ActionVOS, is pointer only (licence: NONE) · get_code("ccbe959ea69981ad")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, buxiangzhiren/vd-it 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.

Also present in other papers' code

Of 20 samples lifted from this paper's linked repositories, 20 carry a function identity and 0 do not. Of the 20 distinct functions with an identity, 19 are also present in other papers whose code we hold (19 with at least one paper dated earlier, 8 the same month, 10 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
NestedTensor
brick of this paper's assembly: helper
32 other papers
29 dated earlier, 1 the same month, 2 later · 28 only as an assembly brick
2005.12872 (2020-05)
End-to-End Object Detection with Transformers
2101.01909 (2021-01)
Line Segment Detection Using Transformers without Edges
2103.04503 (2021-03)
End-to-End Human Object Interaction Detection with HOI Transformer
and 29 more not named here
get_window_size 26 other papers
15 dated earlier, 1 the same month, 9 later, 1 same year, order not determinable · 7 only as an assembly brick
2103.14030 (2021-03)
Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
2106.13230 (2021-06)
Video Swin Transformer
2111.14821 (2021-11)
End-to-End Referring Video Object Segmentation with Multimodal Transformers
and 23 more not named here
aligned_bilinear 17 other papers
14 dated earlier, 1 the same month, 1 later, 1 same year, order not determinable · 1 only as an assembly brick
2201.00487 (2022-01)
Language as Queries for Referring Video Object Segmentation
2203.12827 (2022-03)
Sparse Instance Activation for Real-Time Instance Segmentation
2206.03789 (2022-06)
Language-Bridged Spatial-Temporal Interaction for Referring Video Object Segmentation
and 14 more not named here
window_reverse 16 other papers
11 dated earlier, 1 the same month, 4 later · 5 only as an assembly brick
2003.12039 (2020-03)
RAFT: Recurrent All-Pairs Field Transforms for Optical Flow
2106.13230 (2021-06)
Video Swin Transformer
2111.14821 (2021-11)
End-to-End Referring Video Object Segmentation with Multimodal Transformers
and 13 more not named here
window_partition 15 other papers
12 dated earlier, 1 the same month, 2 later · 2 only as an assembly brick
2106.13230 (2021-06)
Video Swin Transformer
2111.13300 (2021-11)
A Robust Volumetric Transformer for Accurate 3D Tumor Segmentation
2111.14821 (2021-11)
End-to-End Referring Video Object Segmentation with Multimodal Transformers
and 12 more not named here
compute_locations
brick of this paper's assembly: helper
12 other papers
8 dated earlier, 1 the same month, 2 later, 1 same year, order not determinable · 1 only as an assembly brick
2201.00487 (2022-01)
Language as Queries for Referring Video Object Segmentation
2207.14012 (2022-07)
Video Mask Transfiner for High-Quality Video Instance Segmentation
aaai_25201 (2023 (year only))
InstanceFormer: An Online Video Instance Segmentation Framework
and 9 more not named here
box_cxcywh_to_xyxy 9 other papers
5 dated earlier, 1 the same month, 1 later, 2 same year, order not determinable
2103.12115 (2021-03)
End-to-End Trainable Multi-Instance Pose Estimation with Transformers
Pan_Wnet_Audio-Guided_Video_Object_Segmentation_via_Wavelet-Based_Cross-Modal_Denoising_Networks_CVPR_2022_paper (2022 (year only))
Wnet: Audio-Guided Video Object Segmentation via Wavelet-Based Cross-Modal Denoising Networks
2201.00487 (2022-01)
Language as Queries for Referring Video Object Segmentation
and 6 more not named here
rescale_bboxes 7 other papers
4 dated earlier, 1 the same month, 1 later, 1 same year, order not determinable
Pan_Wnet_Audio-Guided_Video_Object_Segmentation_via_Wavelet-Based_Cross-Modal_Denoising_Networks_CVPR_2022_paper (2022 (year only))
Wnet: Audio-Guided Video Object Segmentation via Wavelet-Based Cross-Modal Denoising Networks
2201.00487 (2022-01)
Language as Queries for Referring Video Object Segmentation
2307.09356 (2023-07)
OnlineRefer: A Simple Online Baseline for Referring Video Object Segmentation
and 4 more not named here
vis_add_mask 5 other papers
3 dated earlier, 1 later, 1 same year, order not determinable
2201.00487 (2022-01)
Language as Queries for Referring Video Object Segmentation
2307.09356 (2023-07)
OnlineRefer: A Simple Online Baseline for Referring Video Object Segmentation
2307.13537 (2023-07)
Spectrum-guided Multi-granularity Referring Video Object Segmentation
and 2 more not named here
FeatureResizer
brick of this paper's assembly: helper
3 other papers
3 dated earlier · 1 only as an assembly brick
2209.13306 (2022-09)
Embracing Consistency: A One-Stage Approach for Spatio-Temporal Video Grounding
2307.13537 (2023-07)
Spectrum-guided Multi-granularity Referring Video Object Segmentation
2308.09351 (2023-08)
RLIPv2: Fast Scaling of Relational Language-Image Pre-training
PositionEmbeddingSine1D
brick of this paper's assembly: helper
2 other papers
2 dated earlier · 1 only as an assembly brick
2303.03366 (2023-03)
Referring Multi-Object Tracking
2307.13537 (2023-07)
Spectrum-guided Multi-granularity Referring Video Object Segmentation
parse_dynamic_params
brick of this paper's assembly: helper
2 other papers
1 dated earlier, 1 later
2307.13537 (2023-07)
Spectrum-guided Multi-granularity Referring Video Object Segmentation
2410.20508 (2024-10)
Referring Human Pose and Mask Estimation in the Wild
LFMResizeAdaptive
brick of this paper's assembly: helper
1 other paper
1 dated earlier · 1 only as an assembly brick
2307.13537 (2023-07)
Spectrum-guided Multi-granularity Referring Video Object Segmentation
MSO
brick of this paper's assembly: helper
1 other paper
1 dated earlier · 1 only as an assembly brick
2307.13537 (2023-07)
Spectrum-guided Multi-granularity Referring Video Object Segmentation
RobertaTokenizer
brick of this paper's assembly: helper
1 other paper
1 dated earlier · 1 only as an assembly brick
2307.13537 (2023-07)
Spectrum-guided Multi-granularity Referring Video Object Segmentation
TextEncoder
brick of this paper's assembly: helper
1 other paper
1 dated earlier · 1 only as an assembly brick
2307.13537 (2023-07)
Spectrum-guided Multi-granularity Referring Video Object Segmentation
VisionLanguageFusionModule
brick of this paper's assembly: helper
1 other paper
1 dated earlier · 1 only as an assembly brick
2307.13537 (2023-07)
Spectrum-guided Multi-granularity Referring Video Object Segmentation
_get_src_permutation_idx
brick of this paper's assembly: helper
1 other paper
1 dated earlier · 1 only as an assembly brick
2307.13537 (2023-07)
Spectrum-guided Multi-granularity Referring Video Object Segmentation
nested_tensor_from_videos_list
brick of this paper's assembly: helper
1 other paper
1 dated earlier · 1 only as an assembly brick
2307.13537 (2023-07)
Spectrum-guided Multi-granularity Referring Video Object Segmentation

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 explore the visual representations produced from a pre-trained text-to-video (T2V) diffusion model for video understanding tasks. We hypothesize that the latent representation learned from a pretrained generative T2V model encapsulates rich semantics and coherent temporal correspondences, thereby naturally facilitating video understanding. Our hypothesis is validated through the classic referring video object segmentation (R-VOS) task. We introduce a novel framework, termed "VD-IT", tailored with dedicatedly designed components built upon a fixed pretrained T2V model. Specifically, VD-IT uses textual information as a conditional input, ensuring semantic consistency across time for precise temporal instance matching. It further incorporates image tokens as supplementary textual inputs, enriching the feature set to generate detailed and nuanced masks. Besides, instead of using the standard Gaussian noise, we propose to predict the video-specific noise with an extra noise prediction module, which can help preserve the feature fidelity and elevates segmentation quality. Through extensive experiments, we surprisingly observe that fixed generative T2V diffusion models, unlike commonly used video backbones (e.g., Video Swin Transformer) pretrained with discriminative image/video pre-tasks, exhibit better potential to maintain semantic alignment and temporal consistency. On existing standard benchmarks, our VD-IT achieves highly competitive results, surpassing many existing state-of-the-art methods. The code is available at https://github.com/buxiangzhiren/VD-IT.

For agents

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

get_harvested_code_for_paper("2403.12042")
get_code_for_paper("2403.12042")
have("2403.12042")

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

curl https://syntology.ai/api/ran/2403.12042.json

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

[![Syntology run record](https://syntology.ai/api/ran/2403.12042.svg)](https://syntology.ai/paper/2403.12042)

Connect an agent — have() is free.