Moment Retrieval

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 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. A dash means no Syntology record for that paper, not a recorded non-run. Read from the graph 2026-09-24.

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

6 datasets whose archive record lists this task, ordered by the archive's paper count.

Subtasks archive 2025-07-28

1 subtask in the archive's task tree.

Most implemented papers archive 2025-07-28

30 shown of 76 papers with code (132 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.

• QVHighlights: Detecting Moments and Highlights in Videos via Natural Language Queries
  20 Jul 2021 4 repositories listed Syntology ran 2 of 2 samples · 0 unverified · 1 pointer-only (licence)
  Each video in the dataset is annotated with: (1) a human-written free-form NL query, (2) relevant moments in the video w.
• UMT: Unified Multi-modal Transformers for Joint Video Moment Retrieval and Highlight Detection
  23 Mar 2022 3 repositories listed
  Finding relevant moments and highlights in videos according to natural language queries is a natural and highly valuable common need in the current video content explosion era.
• HERO: Hierarchical Encoder for Video+Language Omni-representation Pre-training
  1 May 2020 3 repositories listed Syntology ran 5 of 13 samples · 8 unverified · 8 pointer-only (licence)
  We present HERO, a novel framework for large-scale video+language omni-representation learning.
• InternVideo2: Scaling Foundation Models for Multimodal Video Understanding
  22 Mar 2024 2 repositories listed
  We introduce InternVideo2, a new family of video foundation models (ViFM) that achieve the state-of-the-art results in video recognition, video-text tasks, and video-centric dialogue.
• Correlation-Guided Query-Dependency Calibration for Video Temporal Grounding
  15 Nov 2023 2 repositories listed Syntology ran 2 of 11 samples · 9 unverified · 11 pointer-only (licence)
  Dummy tokens conditioned by text query take portions of the attention weights, preventing irrelevant video clips from being represented by the text query.
• TVR: A Large-Scale Dataset for Video-Subtitle Moment Retrieval
  24 Jan 2020 2 repositories listed Syntology ran 8 of 19 samples · 11 unverified
  The queries are also labeled with query types that indicate whether each of them is more related to video or subtitle or both, allowing for in-depth analysis of the dataset and the methods that built on top of it.
• Finding Moments in Video Collections Using Natural Language
  30 Jul 2019 2 repositories listed Syntology ran 0 of 11 samples · 11 unverified
  We evaluate our approach on two recently proposed datasets for temporal localization of moments in video with natural language (DiDeMo and Charades-STA) extended to our video corpus moment retrieval setting.
• TimeLoc: A Unified End-to-End Framework for Precise Timestamp Localization in Long Videos
  9 Mar 2025 1 repository listed
  Temporal localization in untrimmed videos, which aims to identify specific timestamps, is crucial for video understanding but remains challenging.
• Moment of Untruth: Dealing with Negative Queries in Video Moment Retrieval
  12 Feb 2025 1 repository listed
  Video Moment Retrieval is a common task to evaluate the performance of visual-language models - it involves localising start and end times of moments in videos from query sentences.
• LD-DETR: Loop Decoder DEtection TRansformer for Video Moment Retrieval and Highlight Detection
  18 Jan 2025 1 repository listed
  Existing models usually first use contrastive learning methods to align video and text features, then fuse and extract multimodal information, and finally use a Transformer Decoder to decode multimodal information.
• A Flexible and Scalable Framework for Video Moment Search
  9 Jan 2025 1 repository listed
  Retrieved segments are then merged into coarse-grained moment proposals.
• Watch Video, Catch Keyword: Context-aware Keyword Attention for Moment Retrieval and Highlight Detection
  5 Jan 2025 1 repository listed Syntology ran 8 of 10 samples · 2 unverified · 10 pointer-only (licence)
  In this paper, we present a novel Video Context-aware Keyword Attention module that overcomes this limitation by capturing keyword variation within the context of the entire video.
• DTOS: Dynamic Time Object Sensing with Large Multimodal Model
  1 Jan 2025 1 repository listed
  We identify three critical challenges: (C1) insufficient quantitative representation of textual numerical data, (C2) repetitive and degraded response templates for spatiotemporal referencing, and (C3) loss of visual…
• Anchor-Aware Similarity Cohesion in Target Frames Enables Predicting Temporal Moment Boundaries in 2D
  1 Jan 2025 1 repository listed
  Video moment retrieval aims to locate specific moments from a video according to the query text.
• Length-Aware DETR for Robust Moment Retrieval
  30 Dec 2024 1 repository listed
  Video Moment Retrieval (MR) aims to localize moments within a video based on a given natural language query.
• FlashVTG: Feature Layering and Adaptive Score Handling Network for Video Temporal Grounding
  18 Dec 2024 1 repository listed Syntology ran 2 of 13 samples · 11 unverified · 13 pointer-only (licence)
  For short-moment retrieval, FlashVTG increases mAP to 125% of previous SOTA performance.
• VideoLights: Feature Refinement and Cross-Task Alignment Transformer for Joint Video Highlight Detection and Moment Retrieval
  2 Dec 2024 1 repository listed
  Video Highlight Detection and Moment Retrieval (HD/MR) are essential in video analysis.
• Vid-Morp: Video Moment Retrieval Pretraining from Unlabeled Videos in the Wild
  1 Dec 2024 1 repository listed
  To support this, we introduce Video Moment Retrieval Pretraining (Vid-Morp), a large-scale dataset collected with minimal human intervention, consisting of over 50K videos captured in the wild and 200K pseudo…
• LLaVA-MR: Large Language-and-Vision Assistant for Video Moment Retrieval
  21 Nov 2024 1 repository listed
  However, long video processing and precise moment retrieval remain challenging due to LLMs' limited context size and coarse frame extraction.
• Number it: Temporal Grounding Videos like Flipping Manga
  15 Nov 2024 1 repository listed Syntology ran 1 of 11 samples · 10 unverified
  Video Large Language Models (Vid-LLMs) have made remarkable advancements in comprehending video content for QA dialogue.
• TimeSuite: Improving MLLMs for Long Video Understanding via Grounded Tuning
  25 Oct 2024 1 repository listed Syntology ran 3 of 6 samples · 3 unverified
  This paper proposes TimeSuite, a collection of new designs to adapt the existing short-form video MLLMs for long video understanding, including a simple yet efficient framework to process long video sequence, a…
• VERIFIED: A Video Corpus Moment Retrieval Benchmark for Fine-Grained Video Understanding
  11 Oct 2024 1 repository listed
  In this paper, we propose a more challenging fine-grained VCMR benchmark requiring methods to localize the best-matched moment from the corpus with other partially matched candidates.
• Saliency-Guided DETR for Moment Retrieval and Highlight Detection
  2 Oct 2024 1 repository listed
  Combined with the introduced Saliency-Guided Cross Attention mechanism and a hybrid DETR architecture, our approach significantly enhances performance in both moment retrieval and highlight detection tasks.
• Show and Guide: Instructional-Plan Grounded Vision and Language Model
  27 Sep 2024 1 repository listed
  Guiding users through complex procedural plans is an inherently multimodal task in which having visually illustrated plan steps is crucial to deliver an effective plan guidance.
• Language-based Audio Moment Retrieval
  24 Sep 2024 1 repository listed
  Additionally, we provide manually annotated datasets to properly measure the effectiveness and robustness of our methods on real data.
• Lighthouse: A User-Friendly Library for Reproducible Video Moment Retrieval and Highlight Detection
  6 Aug 2024 1 repository listed Syntology ran 5 of 11 samples · 6 unverified
  Lighthouse addresses these issues by implementing a unified reproducible codebase that includes six models, three features, and five datasets.
• Prior Knowledge Integration via LLM Encoding and Pseudo Event Regulation for Video Moment Retrieval
  21 Jul 2024 1 repository listed Syntology ran 5 of 11 samples · 6 unverified
  Through a feasibility study, we demonstrate that LLM encoders effectively refine inter-concept relations in multimodal embeddings, even without being trained on textual embeddings.
• TVR-Ranking: A Dataset for Ranked Video Moment Retrieval with Imprecise Queries
  9 Jul 2024 1 repository listed
  To facilitate research in RVMR, we develop the TVR-Ranking dataset, based on the raw videos and existing moment annotations provided in the TVR dataset.
• SHINE: Saliency-aware HIerarchical NEgative Ranking for Compositional Temporal Grounding
  6 Jul 2024 1 repository listed Syntology ran 9 of 13 samples · 4 unverified · 13 pointer-only (licence)
  Temporal grounding, also known as video moment retrieval, aims at locating video segments corresponding to a given query sentence.
• The Surprising Effectiveness of Multimodal Large Language Models for Video Moment Retrieval
  26 Jun 2024 1 repository listed Syntology ran 0 of 1 samples · 1 unverified
  We achieve a new state-of-the-art in moment retrieval on the widely used benchmarks Charades-STA, QVHighlights, and ActivityNet Captions.

Syntology lines on 13 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. Read from the graph 2026-09-24.