Papers › VTG-LLM: Integrating Timestamp Knowledge into Video LLMs for Enhanced Video Temporal Grounding

VTG-LLM: Integrating Timestamp Knowledge into Video LLMs for Enhanced Video Temporal Grounding

22 May 2024arXiv:2405.13382archive 2025-07-28

Yongxin Guo, Jingyu Liu, Mingda Li, Dingxin Cheng, Xiaoying Tang, Dianbo Sui, Qingbin Liu, Xi Chen, Kevin Zhao

Video Temporal Grounding (VTG) strives to accurately pinpoint event timestamps in a specific video using linguistic queries, significantly impacting downstream tasks like video browsing and editing. Unlike traditional task-specific models, Video Large Language Models (video LLMs) can handle multiple tasks concurrently in a zero-shot manner. Consequently, exploring the application of video LLMs for VTG tasks has become a burgeoning research area. However, despite considerable advancements in video content understanding, video LLMs often struggle to accurately pinpoint timestamps within videos, limiting their effectiveness in VTG tasks. To address this, we introduce VTG-LLM, a model designed to enhance video LLMs' timestamp localization abilities. Our approach includes: (1) effectively integrating timestamp knowledge into visual tokens; (2) incorporating absolute-time tokens to manage timestamp knowledge without concept shifts; and (3) introducing a lightweight, high-performance, slot-based token compression technique designed to accommodate the demands of a large number of frames to be sampled for VTG tasks. Additionally, we present VTG-IT-120K, a collection of publicly available VTG datasets that we have re-annotated to improve upon low-quality annotations. Our comprehensive experiments demonstrate the superior performance of VTG-LLM in comparison to other video LLM methods across a variety of VTG tasks.

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2405.13382")

Code

Syntology Ran 13 of 17 code samples harvested from 1 repository linked to this paper; 4 have no recorded run. Of those that ran: 13 ran with no contract checked.

By repository: official repository: 17 samples from 1 repository, 13 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

gyxxyg/vtg-llm officialmentioned in papermentioned on GitHubpytorchApache-2.0 report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

17 samples harvested; 13 ran; 0 honoured the contract we drafted; 4 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

13ran
4unverified

Licence: 0 of the 17 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from gyxxyg/vtg-llm. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

extract_time gyxxyg/vtg-llm/utils/format_tvg.py official repository ran fingerprinted Apache-2.0 (permissive) · c033cc58db86cb93 · report
extract_time_from_para gyxxyg/vtg-llm/utils/format_dvc.py official repository ran fingerprinted Apache-2.0 (permissive) · 856796b6222350db · report
extract_time_part gyxxyg/vtg-llm/utils/format_dvc.py official repository ran fingerprinted Apache-2.0 (permissive) · adfc3585c242cfb2 · report
extract_time_special_time_token gyxxyg/vtg-llm/utils/format_tvg.py official repository ran fingerprinted Apache-2.0 (permissive) · 3223c4fbb3dd41e6 · report
load_data gyxxyg/vtg-llm/evaluate.py official repository ran Apache-2.0 (permissive) · 741e5b0b3aa32a32 · report
merge_seg_caps gyxxyg/vtg-llm/evaluate.py official repository ran Apache-2.0 (permissive) · d650b26a59df9e29 · report
parse_highlights gyxxyg/vtg-llm/utils/format_vhd.py official repository ran fingerprinted Apache-2.0 (permissive) · e7f3262c5969234f · report
parse_highlights_special_time_token gyxxyg/vtg-llm/utils/format_vhd.py official repository ran fingerprinted Apache-2.0 (permissive) · 4eccf153227f2e66 · report
prepare_input_output_pairs gyxxyg/vtg-llm/utils/compress_video_data.py official repository ran Apache-2.0 (permissive) · 5d0935bf83ca723a · report
read_json gyxxyg/vtg-llm/utils/format_dvc.py official repository ran Apache-2.0 (permissive) · 7aad81b5c188085c · report
read_txt gyxxyg/vtg-llm/evaluate.py official repository ran Apache-2.0 (permissive) · e49f0cf401af904b · report
time_to_seconds gyxxyg/vtg-llm/utils/parse_annotation_dvc.py official repository ran Apache-2.0 (permissive) · 8c2ceabd4b50b073 · report
time_to_seconds_B gyxxyg/vtg-llm/utils/parse_annotation_dvc.py official repository ran fingerprinted Apache-2.0 (permissive) · 29c4fd20bc454255 · report
random_string gyxxyg/vtg-llm/metrics/dvc/eval_dvc_anet.py official repository unverified Apache-2.0 (permissive) · cfb0aa2342a41918 · report
read_jsonl gyxxyg/vtg-llm/utils/get_coco_format.py official repository unverified Apache-2.0 (permissive) · 8871a34f67963cf7 · report
remove_nonascii gyxxyg/vtg-llm/metrics/dvc/eval_dvc_anet.py official repository unverified Apache-2.0 (permissive) · a45f62024eb3d2c5 · report
time_to_seconds_B gyxxyg/vtg-llm/utils/parse_annotation_vhd.py official repository unverified Apache-2.0 (permissive) · f6211c4b35fc395b · report

Tasks

Dense Video CaptioningHighlight DetectionMoment RetrievalVideo CaptioningVideo Summarization

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections