mlsanityData to 14 Oct 2026

SnAG: Scalable and Accurate Video Grounding

arXiv 2404.02257 ↗First posted 2 Apr 2024cs.CVcited by 36

Not on the map. Why?

Abstract (arXiv)

Temporal grounding of text descriptions in videos is a central problem in vision-language learning and video understanding. Existing methods often prioritize accuracy over scalability -- they have been optimized for grounding only a few text queries within short videos, and fail to scale up to long videos with hundreds of queries. In this paper, we study the effect of cross-modal fusion on the scalability of video grounding models. Our analysis establishes late fusion as a more cost-effective fusion scheme for long-form videos with many text queries. Moreover, it leads us to a novel, video-centric sampling scheme for efficient training. Based on these findings, we present SnAG, a simple baseline for scalable and accurate video grounding. Without bells and whistles, SnAG is 43% more accurate and 1.5x faster than CONE, a state of the art for long-form video grounding on the challenging MAD dataset, while achieving highly competitive results on short videos.

Key facts. Cited by 36 papers in the map (data through 14 Oct 2026). Builds on 52 of its 77 references that are in the map. First posted on arXiv 2 Apr 2024.

Builds on

52 of 77 references.

References · 52

  1. 2017Attention Is All You Needcited by 60,361
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  4. 2016Layer Normalizationcited by 5,669
  5. 2017Quo Vadis, Action Recognition? A New Model and the Kinetics Datasetcited by 3,270
  6. 2017The Kinetics Human Action Video Datasetcited by 1,909
  7. 2018SlowFast Networks for Video Recognitioncited by 1,867
  8. 2019FCOS: Fully Convolutional One-Stage Object Detectioncited by 1,577
  9. 2021Ego4D: Around the World in 3,000 Hours of Egocentric Videocited by 1,556
  10. 2017Dense-Captioning Events in Videoscited by 793
  11. 2017Localizing Moments in Video with Natural Languagecited by 663
  12. 2017TALL: Temporal Activity Localization via Language Querycited by 584
38 more
  1. 2016Hollywood in Homes: Crowdsourcing Data Collection for Activity Understandingcited by 537
  2. 2019Distance-IoU Loss: Faster and Better Learning for Bounding Box Regressioncited by 459
  3. 2017Soft-NMS -- Improving Object Detection With One Line of Codecited by 382
  4. 2019Learning 2D Temporal Adjacent Networks for Moment Localization with Natural Languagecited by 285
  5. 2020Span-based Localizing Network for Natural Language Video Localizationcited by 235
  6. 2022Egocentric Video-Language Pretrainingcited by 232
  7. 2023UniVTG: Towards Unified Video-Language Temporal Groundingcited by 190
  8. 2020Local-Global Video-Text Interactions for Temporal Groundingcited by 188
  9. 2020Dense Regression Network for Video Groundingcited by 176
  10. 2018To Find Where You Talk: Temporal Sentence Localization in Video with Attention Based Location Regressioncited by 157
  11. 2018MAN: Moment Alignment Network for Natural Language Moment Retrieval via Iterative Graph Adjustmentcited by 145
  12. 2019Semantic Conditioned Dynamic Modulation for Temporal Sentence Grounding in Videoscited by 135
  13. 2018Multilevel Language and Vision Integration for Text-to-Clip Retrievalcited by 128
  14. 2021MAD: A Scalable Dataset for Language Grounding in Videos from Movie Audio Descriptionscited by 108
  15. 2021Context-aware Biaffine Localizing Network for Temporal Sentence Groundingcited by 107
  16. 2021Interventional Video Grounding with Dual Contrastive Learningcited by 94
  17. 2021Negative Sample Matters: A Renaissance of Metric Learning for Temporal Groundingcited by 90
  18. 2021Boundary Proposal Network for Two-Stage Natural Language Video Localizationcited by 88
  19. 2019Weakly Supervised Video Moment Retrieval From Text Queriescited by 85
  20. 2019Temporally Grounding Language Queries in Videos by Contextual Boundary-aware Predictioncited by 84
  21. 2019ExCL: Extractive Clip Localization Using Natural Language Descriptionscited by 82
  22. 2019Proposal-free Temporal Moment Localization of a Natural-Language Query in Video using Guided Attentioncited by 81
  23. 2022Compositional Temporal Grounding with Structured Variational Cross-Graph Correspondence Learningcited by 59
  24. 2020Uncovering Hidden Challenges in Query-Based Video Moment Retrievalcited by 58
  25. 2020VLG-Net: Video-Language Graph Matching Network for Video Groundingcited by 50
  26. 2022Memory-Guided Semantic Learning Network for Temporal Sentence Groundingcited by 46
  27. 2021A Closer Look at Temporal Sentence Grounding in Videos: Dataset and Metriccited by 42
  28. 2021Adaptive Proposal Generation Network for Temporal Sentence Localization in Videoscited by 42
  29. 2023You Can Ground Earlier than See: An Effective and Efficient Pipeline for Temporal Sentence Grounding in Compressed Videoscited by 41
  30. 2021Progressively Guide to Attend: An Iterative Alignment Framework for Temporal Sentence Groundingcited by 31
  31. 2021Embracing Uncertainty: Decoupling and De-bias for Robust Temporal Groundingcited by 29
  32. 2021Natural Language Video Localization with Learnable Moment Proposalscited by 27
  33. 2021Relation-aware Video Reading Comprehension for Temporal Language Groundingcited by 27
  34. 2022CONE: An Efficient COarse-to-fiNE Alignment Framework for Long Video Temporal Groundingcited by 27
  35. 2023Localizing Moments in Long Video Via Multimodal Guidancecited by 23
  36. 2023Scanning Only Once: An End-to-end Framework for Fast Temporal Grounding in Long Videoscited by 23
  37. 2021Parallel Attention Network with Sequence Matching for Video Groundingcited by 22
  38. 2023G2L: Semantically Aligned and Uniform Video Grounding via Geodesic and Game Theorycited by 21

50 most cited of 52 All 52 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 5; 2025: 17; 2026: 14.

36 papers.

Sort:

By area:

  1. 2025Time-R1: Post-Training Large Vision Language Model for Temporal Video Groundingcited by 146
  2. 2024Grounded Multi-Hop VideoQA in Long-Form Egocentric Videoscited by 45
  3. 2025Universal Video Temporal Grounding with Generative Multi-modal Large Language Modelscited by 27
  4. 2024LinVT: Empower Your Image-level Large Language Model to Understand Videoscited by 19
  5. 2024ReVisionLLM: Recursive Vision-Language Model for Temporal Grounding in Hour-Long Videoscited by 18
  6. 2025TempSamp-R1: Effective Temporal Sampling with Reinforcement Fine-Tuning for Video LLMscited by 15
  7. 2024SEAL: Semantic Attention Learning for Long Video Representationcited by 13
  8. 2025SocialGesture: Delving into Multi-person Gesture Understandingcited by 11
  9. 2025Object-Shot Enhanced Grounding Network for Egocentric Videocited by 11
  10. 2026Video2GUI: Synthesizing Large-Scale Interaction Trajectories for Generalized GUI Agent Pretrainingcited by 7
  11. 2026CutClaw: Agentic Hours-Long Video Editing via Music Synchronizationcited by 6
  12. 2024Multi-Scale Contrastive Learning for Video Temporal Groundingcited by 5
24 more
  1. 2025DeCafNet: Delegate and Conquer for Efficient Temporal Grounding in Long Videoscited by 5
  2. 2025Hierarchical Event Memory for Accurate and Low-latency Online Video Temporal Groundingcited by 5
  3. 2025TimeScope: Towards Task-Oriented Temporal Grounding In Long Videoscited by 5
  4. 2025Seeing without Pixels: Perception from Camera Trajectoriescited by 4
  5. 2026ArrowGEV: Grounding Events in Video via Learning the Arrow of Timecited by 4
  6. 2026OmniVTG: A Large-Scale Dataset and Training Paradigm for Open-World Video Temporal Groundingcited by 4
  7. 2025The Devil is in the Spurious Correlations: Boosting Moment Retrieval with Dynamic Learningcited by 3
  8. 2025TimeLoc: A Unified End-to-End Framework for Precise Timestamp Localization in Long Videoscited by 3
  9. 2025Learning to Refuse: Refusal-Aware Reinforcement Fine-Tuning for Hard-Irrelevant Queries in Video Temporal Groundingcited by 3
  10. 2026Temporal-Aware Reasoning Optimization for Video Temporal Groundingcited by 3
  11. 2025ResidualViT for Efficient Temporally Dense Video Encodingcited by 2
  12. 2025Point to Span: Zero-Shot Moment Retrieval for Navigating Unseen Hour-Long Videoscited by 2
  13. 2025Object-Centric Framework for Video Moment Retrievalcited by 2
  14. 2026Finding Optimal Video Moment without Training: Gaussian Boundary Optimization for Weakly Supervised Video Groundingcited by 2
  15. 2025HieraMamba: Video Temporal Grounding via Hierarchical Anchor-Mamba Poolingcited by 1
  16. 2026DRIFT: A Residual Flow Adapter for Decoding Continuous Outputs in Vision-Language Modelscited by 1
  17. 2026ESTANet: Efficient Online Error Detection in Procedural Videos via Prediction Inconsistencycited by 1
  18. 2025OVG-HQ: Online Video Grounding with Hybrid-modal Queriescited by 0
  19. 2026RatSeizure: A Benchmark and Saliency-Context Transformer for Rat Seizure Localizationcited by 0
  20. 2026UniversalVTG: A Universal and Lightweight Foundation Model for Video Temporal Groundingcited by 0
  21. 2026Interactive Episodic Memory with User Feedbackcited by 0
  22. 2026StoryVideoQA: Scaling Deep Video Understanding with a Large-Scale, Multi-Genre and Auto-Generated Datasetcited by 0
  23. 2026D'ej`a Cue: Localizing States in Object Histories via Vocabulary-Relative Coordinatescited by 0
  24. 2026ID-VTG: Image-Disambiguated Video Temporal Groundingcited by 0