mlsanityData to 7 Oct 2026

WSLLN: Weakly Supervised Natural Language Localization Networks

arXiv 1909.00239 ↗First posted 31 Aug 2019cs.CVcited by 36

Not on the map. Why?

Abstract (arXiv)

We propose weakly supervised language localization networks (WSLLN) to detect events in long, untrimmed videos given language queries. To learn the correspondence between visual segments and texts, most previous methods require temporal coordinates (start and end times) of events for training, which leads to high costs of annotation. WSLLN relieves the annotation burden by training with only video-sentence pairs without accessing to temporal locations of events. With a simple end-to-end structure, WSLLN measures segment-text consistency and conducts segment selection (conditioned on the text) simultaneously. Results from both are merged and optimized as a video-sentence matching problem. Experiments on ActivityNet Captions and DiDeMo demonstrate that WSLLN achieves state-of-the-art performance.

Key facts. Cited by 36 papers in the map (data through 7 Oct 2026). First posted on arXiv 31 Aug 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 10; 2022: 7; 2023: 11; 2024: 2; 2025: 1; 2026: 5.

36 papers.

Sort:

By area:

  1. 2023Can I Trust Your Answer? Visually Grounded Video Question Answeringcited by 133
  2. 2021A Closer Look at Temporal Sentence Grounding in Videos: Dataset and Metriccited by 42
  3. 2021Cross-Sentence Temporal and Semantic Relations in Video Activity Localisationcited by 39
  4. 2021Weakly Supervised Temporal Adjacent Network for Language Groundingcited by 37
  5. 2022Temporal Sentence Grounding in Videos: A Survey and Future Directionscited by 37
  6. 2021Zero-shot Natural Language Video Localizationcited by 34
  7. 2021A Survey on Temporal Sentence Grounding in Videoscited by 29
  8. 2022Language-free Training for Zero-shot Video Groundingcited by 22
  9. 2022Video Moment Retrieval from Text Queries via Single Frame Annotationcited by 19
  10. 2023Variational Cross-Graph Reasoning and Adaptive Structured Semantics Learning for Compositional Temporal Groundingcited by 19
  11. 2023A Survey on Video Moment Localizationcited by 18
  12. 2023Grounding-Prompter: Prompting LLM with Multimodal Information for Temporal Sentence Grounding in Long Videoscited by 14
24 more
  1. 2023SCANet: Scene Complexity Aware Network for Weakly-Supervised Video Moment Retrievalcited by 13
  2. 2021Towards Debiasing Temporal Sentence Grounding in Videocited by 11
  3. 2022A Closer Look at Debiased Temporal Sentence Grounding in Videos: Dataset, Metric, and Approachcited by 11
  4. 2022Weakly-Supervised Temporal Article Groundingcited by 11
  5. 2021Video and Text Matching with Conditioned Embeddingscited by 10
  6. 2023D3G: Exploring Gaussian Prior for Temporal Sentence Grounding with Glance Annotationcited by 8
  7. 2026Rethinking Weakly-supervised Video Temporal Grounding From a Game Perspectivecited by 8
  8. 2021Self-supervised Learning for Semi-supervised Temporal Language Groundingcited by 7
  9. 2023Counterfactual Cross-modality Reasoning for Weakly Supervised Video Moment Localizationcited by 7
  10. 2021A Survey on Natural Language Video Localizationcited by 6
  11. 2026Video Understanding: From Geometry and Semantics to Unified Modelscited by 5
  12. 2023Zero-Shot Dense Video Captioning by Jointly Optimizing Text and Momentcited by 4
  13. 2023EtC: Temporal Boundary Expand then Clarify for Weakly Supervised Video Grounding with Multimodal Large Language Modelcited by 4
  14. 2023Commonsense for Zero-Shot Natural Language Video Localizationcited by 4
  15. 2022Fine-grained Semantic Alignment Network for Weakly Supervised Temporal Language Groundingcited by 3
  16. 2021Multi-scale 2D Representation Learning for weakly-supervised moment retrievalcited by 2
  17. 2025Weakly Supervised Temporal Sentence Grounding via Positive Sample Miningcited by 2
  18. 2022Multi-Scale Self-Contrastive Learning with Hard Negative Mining for Weakly-Supervised Query-based Video Groundingcited by 1
  19. 2024Hybrid-Learning Video Moment Retrieval across Multi-Domain Labelscited by 1
  20. 2026DART: Difficulty-Adaptive Routing for Zero-Shot Video Temporal Groundingcited by 1
  21. 2023Focusing On Targets For Improving Weakly Supervised Visual Groundingcited by 0
  22. 2024AutoTVG: A New Vision-language Pre-training Paradigm for Temporal Video Groundingcited by 0
  23. 2026Multi-proposal Collaboration and Multi-task Training for Weakly-supervised Video Moment Retrievalcited by 0
  24. 2026What You Ask is What You Ground: Bridging Question Intent to Temporal Evidence for Grounded VideoQAcited by 0