{"total":50,"rows":[{"id":"2205.14100","title":"GIT: A Generative Image-to-text Transformer for Vision and Language","created":"2022-05-27","cited_by_count":537,"area":null},{"id":"2111.13196","title":"SwinBERT: End-to-End Transformers with Sparse Attention for Video Captioning","created":"2021-11-25","cited_by_count":162,"area":null},{"id":"2103.11555","title":"Context-aware Biaffine Localizing Network for Temporal Sentence Grounding","created":"2021-03-22","cited_by_count":107,"area":null},{"id":"2109.04872","title":"Negative Sample Matters: A Renaissance of Metric Learning for Temporal Grounding","created":"2021-09-10","cited_by_count":90,"area":null},{"id":"2105.06247","title":"Video Corpus Moment Retrieval with Contrastive Learning","created":"2021-05-13","cited_by_count":60,"area":null},{"id":"2102.13558","title":"Natural Language Video Localization: A Revisit in Span-based Question Answering Framework","created":"2021-02-26","cited_by_count":55,"area":null},{"id":"2201.00454","title":"Memory-Guided Semantic Learning Network for Temporal Sentence Grounding","created":"2022-01-03","cited_by_count":46,"area":null},{"id":"2203.05203","title":"MORE: Multi-Order RElation Mining for Dense Captioning in 3D Scenes","created":"2022-03-10","cited_by_count":46,"area":null},{"id":"2103.05284","title":"Open-book Video Captioning with Retrieve-Copy-Generate Network","created":"2021-03-09","cited_by_count":43,"area":null},{"id":"2201.08071","title":"Temporal Sentence Grounding in Videos: A Survey and Future Directions","created":"2022-01-20","cited_by_count":37,"area":null},{"id":"2203.02966","title":"Exploring Optical-Flow-Guided Motion and Detection-Based Appearance for Temporal Sentence Grounding","created":"2022-03-06","cited_by_count":35,"area":null},{"id":"2207.13457","title":"Reducing the Vision and Language Bias for Temporal Sentence Grounding","created":"2022-07-27","cited_by_count":35,"area":null},{"id":"2311.08835","title":"Correlation-Guided Query-Dependency Calibration for Video Temporal Grounding","created":"2023-11-15","cited_by_count":31,"area":null},{"id":"2407.15051","title":"Prior Knowledge Integration via LLM Encoding and Pseudo Event Regulation for Video Moment Retrieval","created":"2024-07-21","cited_by_count":30,"area":null},{"id":"2109.08039","title":"A Survey on Temporal Sentence Grounding in Videos","created":"2021-09-16","cited_by_count":29,"area":null},{"id":"2304.11431","title":"A Review of Deep Learning for Video Captioning","created":"2023-04-22","cited_by_count":28,"area":null},{"id":"2105.08481","title":"Parallel Attention Network with Sequence Matching for Video Grounding","created":"2021-05-18","cited_by_count":22,"area":null},{"id":"2207.14698","title":"Can Shuffling Video Benefit Temporal Bias Problem: A Novel Training Framework for Temporal Grounding","created":"2022-07-29","cited_by_count":22,"area":null},{"id":"2308.06009","title":"ViGT: Proposal-free Video Grounding with Learnable Token in Transformer","created":"2023-08-11","cited_by_count":22,"area":null},{"id":"2309.12867","title":"Accurate and Fast Compressed Video Captioning","created":"2023-09-22","cited_by_count":22,"area":null},{"id":"2403.17935","title":"OmniVid: A Generative Framework for Universal Video Understanding","created":"2024-03-26","cited_by_count":22,"area":null},{"id":"2204.09409","title":"Video Moment Retrieval from Text Queries via Single Frame Annotation","created":"2022-04-20","cited_by_count":19,"area":null},{"id":"2303.15616","title":"Fine-grained Audible Video Description","created":"2023-03-27","cited_by_count":18,"area":null},{"id":"2306.07515","title":"A Survey on Video Moment Localization","created":"2023-06-13","cited_by_count":18,"area":null},{"id":"2102.01282","title":"Progressive Localization Networks for Language-based Moment Localization","created":"2021-02-02","cited_by_count":17,"area":null},{"id":"2104.04369","title":"Video-aided Unsupervised Grammar Induction","created":"2021-04-09","cited_by_count":17,"area":null},{"id":"2302.09850","title":"Constraint and Union for Partially-Supervised Temporal Sentence Grounding","created":"2023-02-20","cited_by_count":14,"area":null},{"id":"2410.08593","title":"VERIFIED: A Video Corpus Moment Retrieval Benchmark for Fine-Grained Video Understanding","created":"2024-10-11","cited_by_count":10,"area":null},{"id":"2502.08544","title":"Moment of Untruth: Dealing with Negative Queries in Video Moment Retrieval","created":"2025-02-12","cited_by_count":10,"area":null},{"id":"2405.12540","title":"Context-Enhanced Video Moment Retrieval with Large Language Models","created":"2024-05-21","cited_by_count":9,"area":null},{"id":"2406.17880","title":"MLLM as Video Narrator: Mitigating Modality Imbalance in Video Moment Retrieval","created":"2024-06-25","cited_by_count":9,"area":null},{"id":"2504.13035","title":"Prototypes are Balanced Units for Efficient and Effective Partially Relevant Video Retrieval","created":"2025-04-17","cited_by_count":8,"area":null},{"id":"2109.11475","title":"Self-supervised Learning for Semi-supervised Temporal Language Grounding","created":"2021-09-23","cited_by_count":7,"area":null},{"id":"2104.00234","title":"A Survey on Natural Language Video Localization","created":"2021-04-01","cited_by_count":6,"area":null},{"id":"2406.10079","title":"Localizing Events in Videos with Multimodal Queries","created":"2024-06-14","cited_by_count":6,"area":null},{"id":"2204.12293","title":"Contrastive Language-Action Pre-training for Temporal Localization","created":"2022-04-26","cited_by_count":5,"area":null},{"id":"2111.00417","title":"Hierarchical Deep Residual Reasoning for Temporal Moment Localization","created":"2021-10-31","cited_by_count":4,"area":null},{"id":"2303.01046","title":"Jointly Visual- and Semantic-Aware Graph Memory Networks for Temporal Sentence Localization in Videos","created":"2023-03-02","cited_by_count":4,"area":null},{"id":"2109.02925","title":"Learning to Combine the Modalities of Language and Video for Temporal Moment Localization","created":"2021-09-07","cited_by_count":3,"area":null},{"id":"2201.10168","title":"Explore-And-Match: Bridging Proposal-Based and Proposal-Free With Transformer for Sentence Grounding in Videos","created":"2022-01-25","cited_by_count":3,"area":null},{"id":"2305.04123","title":"Transform-Equivariant Consistency Learning for Temporal Sentence Grounding","created":"2023-05-06","cited_by_count":3,"area":null},{"id":"2310.17395","title":"Learning Temporal Sentence Grounding From Narrated EgoVideos","created":"2023-10-26","cited_by_count":3,"area":null},{"id":"2411.02851","title":"Learning to Unify Audio, Visual and Text for Audio-Enhanced Multilingual Visual Answer Localization","created":"2024-11-05","cited_by_count":3,"area":null},{"id":"2503.24096","title":"DANTE-AD: Dual-Vision Attention Network for Long-Term Audio Description","created":"2025-03-31","cited_by_count":3,"area":null},{"id":"2205.03039","title":"Dual-Level Decoupled Transformer for Video Captioning","created":"2022-05-06","cited_by_count":2,"area":null},{"id":"2503.14559","title":"Squeeze Out Tokens from Sample for Finer-Grained Data Governance","created":"2025-03-18","cited_by_count":2,"area":null},{"id":"2504.08384","title":"Towards Efficient and Robust Moment Retrieval System: A Unified Framework for Multi-Granularity Models and Temporal Reranking","created":"2025-04-11","cited_by_count":2,"area":null},{"id":"2508.04273","title":"Audio Does Matter: Importance-Aware Multi-Granularity Fusion for Video Moment Retrieval","created":"2025-08-06","cited_by_count":2,"area":null},{"id":"2410.16624","title":"EVC-MF: End-to-end Video Captioning Network with Multi-scale Features","created":"2024-10-22","cited_by_count":0,"area":null},{"id":"2508.11313","title":"Denoise-then-Retrieve: Text-Conditioned Video Denoising for Video Moment Retrieval","created":"2025-08-15","cited_by_count":0,"area":null}],"next_cursor":null}