Browse State-of-the-Art › Temporal Sentence Grounding
Temporal Sentence Grounding
16 papers with code · 2 benchmarks · 1 dataset archive 2025-07-28
Temporal sentence grounding (TSG) aims to locate a specific moment from an untrimmed video with a given natural language query. For this task, different levels of supervision are used. 1) Weak supervision: video-level action category set; 2) Semi-weak supervision: video-level action category set, and action annotations at several timestamps; 3) Full supervision: Action category and action interval annotations of all actions in untrimmed videos.
Description from the archive archive 2025-07-28.
Benchmarks archive 2025-07-28
2 leaderboard tables shown for this task, 2 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted.
Syntology 1 newer paper was judged to report on this task's benchmarks so far (Claude Sonnet 4.5, reading their tables: a model's judgement, not a result; 0 placed): Charades-STA (1 judged, 0 placed). Drawn from 8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read).
| Dataset | Best model (first row in archive order) | Paper | Code | Syntology | Compare |
|---|---|---|---|---|---|
| Charades-STA (13 rows) | DeCafNet | DeCafNet: Delegate and Conquer for Efficient Temporal Grounding in... | code | — | Compare |
| Ego4D-Goalstep (3 rows) | DeCafNet-100% | DeCafNet: Delegate and Conquer for Efficient Temporal Grounding in... | code | — | Compare |
Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. Each line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the row's paper, the line starts with that repository's state (“official” is the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. A dash means no Syntology record for that paper, not a recorded non-run. Each “ran” line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
Libraries
Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.
Datasets archive 2025-07-28
1 dataset whose archive record lists this task, ordered by the archive's paper count.
Subtasks archive 2025-07-28
No subtask under this task in the archive's task tree.
Parent tasks archive 2025-07-28
Papers archive 2025-07-28
archive papers tagged: 43 · with a code link: 16 · where Syntology ran a sample: 7 (5 with a run with no instrument failure, 2 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (7 of 43 tagged: 5 with a run with no instrument failure, 2 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 43 of 43, in archive order: by repositories listed in the archive (most first), then newest first, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers that list no repository come after every paper that lists one.
Papers without a page here are shown as plain text. A Syntology line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code); hover it for the repositories the samples that ran came from. The first sentence of the abstract is shown for the first 30 papers; every abstract is on its paper's page.
-
10 Sep 2021 2 repositories listedInstead, from a perspective on temporal grounding as a metric-learning problem, we present a Mutual Matching Network (MMN), to directly model the similarity between language queries and video moments in a joint…
-
22 May 2025 1 repository listedThe approach taken by existing methods of dividing video into clips and processing each clip via a full-scale expert encoder is challenging to scale due to prohibitive computational costs of processing a large number of…
-
4 Oct 2024 1 repository listed Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample) · 1 pointer-only (licence)Video Large Language Models (Video-LLMs) have demonstrated remarkable capabilities in coarse-grained video understanding, however, they struggle with fine-grained temporal grounding.
-
13 Sep 2024 1 repository listedIn this paper, we address a challenging task, synchronous motion captioning, that aim to generate a language description synchronized with human motion sequences.
-
31 May 2024 1 repository listedTo tackle this limitation, we present a Region-Guided TRansformer (RGTR) for temporal sentence grounding, which diversifies moment queries to eliminate overlapped and redundant predictions.
-
15 Jan 2024 1 repository listed Syntology official (archive's flag): 7 ran · 7 ran (of which 3 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified (of 7 harvested samples) · 7 pointer-only (licence)Temporal Sentence Grounding in Video (TSGV) is troubled by dataset bias issue, which is caused by the uneven temporal distribution of the target moments for samples with similar semantic components in input videos or…
-
27 Dec 2023 1 repository listedIn the weakly supervised temporal video grounding study, previous methods use predetermined single Gaussian proposals which lack the ability to express diverse events described by the sentence query.
-
30 Nov 2023 1 repository listed Syntology official (archive's flag): 9 ran · 9 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified (of 11 harvested samples) · 11 pointer-only (licence)This separate design allows the model to focus on desirable regions, enabling precise refinement of moment predictions.
-
26 Oct 2023 1 repository listedCompared to traditional benchmarks on which this task is evaluated, these datasets offer finer-grained sentences to ground in notably longer videos.
-
14 Aug 2023 1 repository listedThe goal of TSGSV is to evaluate the relevance between a video stream and a given sentence query.
-
8 Aug 2023 1 repository listed Syntology official (archive's flag): 13 ran · 13 ran (of which 5 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 7 where Syntology's instrument failed) · 4 unverified (of 17 harvested samples) · 17 pointer-only (licence)Under this setup, we propose a Dynamic Gaussian prior based Grounding framework with Glance annotation (D3G), which consists of a Semantic Alignment Group Contrastive Learning module (SA-GCL) and a Dynamic Gaussian…
-
7 Aug 2023 1 repository listedTo tackle this problem, we propose a novel efficient multi-teacher model (EMTM) based on knowledge distillation to transfer diverse knowledge from both heterogeneous and isomorphic networks.
-
1 Jan 2022 1 repository listedMoreover, they train their model to distinguish positive visual-language pairs from negative ones randomly collected from other videos, ignoring the highly confusing video segments within the same video.
-
1 Sep 2020 1 repository listed Syntology 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified (of 5 harvested samples)In this paper, we present a series of experiments assessing how well the benchmark results reflect the true progress in solving the moment retrieval task.
-
29 Apr 2020 1 repository listed Syntology official (archive's flag): 5 ran · 5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified (of 8 harvested samples) · 1 pointer-only (licence)Given an untrimmed video and a text query, natural language video localization (NLVL) is to locate a matching span from the video that semantically corresponds to the query.
-
31 Oct 2019 1 repository listed Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified (of 2 harvested samples) · 2 pointer-only (licence)Temporal sentence grounding in videos aims to detect and localize one target video segment, which semantically corresponds to a given sentence.
-
Weakly Supervised Temporal Sentence Grounding via Positive Sample Mining10 May 2025 0 repositories listedThe task of weakly supervised temporal sentence grounding (WSTSG) aims to detect temporal intervals corresponding to a language description from untrimmed videos with only video-level video-language correspondence.
-
Contrast-Unity for Partially-Supervised Temporal Sentence Grounding18 Feb 2025 0 repositories listedTemporal sentence grounding aims to detect event timestamps described by the natural language query from given untrimmed videos.
-
Diversified Augmentation with Domain Adaptation for Debiased Video Temporal Grounding12 Jan 2025 0 repositories listedTemporal sentence grounding in videos (TSGV) faces challenges due to public TSGV datasets containing significant temporal biases, which are attributed to the uneven temporal distributions of target moments.
-
Multi-Pair Temporal Sentence Grounding via Multi-Thread Knowledge Transfer Network20 Dec 2024 0 repositories listedGiven some video-query pairs with untrimmed videos and sentence queries, temporal sentence grounding (TSG) aims to locate query-relevant segments in these videos.
-
Video sentence grounding with temporally global textual knowledge21 Apr 2024 0 repositories listedTemporal sentence grounding involves the retrieval of a video moment with a natural language query.
-
Grounding-Prompter: Prompting LLM with Multimodal Information for Temporal Sentence Grounding in Long Videos28 Dec 2023 0 repositories listedTemporal Sentence Grounding (TSG), which aims to localize moments from videos based on the given natural language queries, has attracted widespread attention.
-
28 Nov 2023 0 repositories listedDeveloping end-to-end action recognition models on long videos is fundamental and crucial for long-video action understanding.
-
Transform-Equivariant Consistency Learning for Temporal Sentence Grounding6 May 2023 0 repositories listedThis paper addresses the temporal sentence grounding (TSG).
-
You Can Ground Earlier than See: An Effective and Efficient Pipeline for Temporal Sentence Grounding in Compressed Videos14 Mar 2023 0 repositories listedGiven an untrimmed video, temporal sentence grounding (TSG) aims to locate a target moment semantically according to a sentence query.
-
Tracking Objects and Activities with Attention for Temporal Sentence Grounding21 Feb 2023 0 repositories listedTemporal sentence grounding (TSG) aims to localize the temporal segment which is semantically aligned with a natural language query in an untrimmed video.Most existing methods extract frame-grained features or…
-
Constraint and Union for Partially-Supervised Temporal Sentence Grounding20 Feb 2023 0 repositories listedTemporal sentence grounding aims to detect the event timestamps described by the natural language query from given untrimmed videos.
-
Rethinking the Video Sampling and Reasoning Strategies for Temporal Sentence Grounding2 Jan 2023 0 repositories listedTemporal sentence grounding (TSG) aims to identify the temporal boundary of a specific segment from an untrimmed video by a sentence query.
-
Weakly Supervised Temporal Sentence Grounding With Uncertainty-Guided Self-Training1 Jan 2023 0 repositories listedThe task of weakly supervised temporal sentence grounding aims at finding the corresponding temporal moments of a language description in the video, given video-language correspondence only at video-level.
-
Learning to Focus on the Foreground for Temporal Sentence Grounding1 Oct 2022 0 repositories listedTemporal sentence grounding (TSG) is crucial and fundamental for video understanding.
-
Hierarchical Local-Global Transformer for Temporal Sentence Grounding31 Aug 2022 0 repositories listed
-
Reducing the Vision and Language Bias for Temporal Sentence Grounding27 Jul 2022 0 repositories listed
-
Towards Visual-Prompt Temporal Answering Grounding in Medical Instructional Video13 Mar 2022 0 repositories listed
-
A Closer Look at Debiased Temporal Sentence Grounding in Videos: Dataset, Metric, and Approach10 Mar 2022 0 repositories listed
-
Exploring Optical-Flow-Guided Motion and Detection-Based Appearance for Temporal Sentence Grounding6 Mar 2022 0 repositories listed
-
Temporal Sentence Grounding in Videos: A Survey and Future Directions20 Jan 2022 0 repositories listed
-
Exploring Motion and Appearance Information for Temporal Sentence Grounding3 Jan 2022 0 repositories listed
-
Memory-Guided Semantic Learning Network for Temporal Sentence Grounding3 Jan 2022 0 repositories listed
-
Towards Debiasing Temporal Sentence Grounding in Video8 Nov 2021 0 repositories listed
-
A Survey on Temporal Sentence Grounding in Videos16 Sep 2021 0 repositories listed
-
Progressively Guide to Attend: An Iterative Alignment Framework for Temporal Sentence Grounding14 Sep 2021 0 repositories listed
-
Context-aware Biaffine Localizing Network for Temporal Sentence Grounding22 Mar 2021 0 repositories listed
-
A Closer Look at Temporal Sentence Grounding in Videos: Dataset and Metric22 Jan 2021 0 repositories listed
Syntology lines on 7 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced; each line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
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