{"total":36,"rows":[{"id":"2306.07207","title":"Valley: Video Assistant with Large Language model Enhanced abilitY","created":"2023-06-12","cited_by_count":234,"area":null},{"id":"2302.10035","title":"Large-scale Multi-Modal Pre-trained Models: A Comprehensive Survey","created":"2023-02-20","cited_by_count":153,"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":"2106.04632","title":"VALUE: A Multi-Task Benchmark for Video-and-Language Understanding Evaluation","created":"2021-06-08","cited_by_count":95,"area":null},{"id":"2210.06031","title":"Long-Form Video-Language Pre-Training with Multimodal Temporal Contrastive Learning","created":"2022-10-12","cited_by_count":59,"area":null},{"id":"2406.19255","title":"Enhancing Video-Language Representations with Structural Spatio-Temporal Alignment","created":"2024-06-27","cited_by_count":32,"area":null},{"id":"2112.04888","title":"A Bilingual, OpenWorld Video Text Dataset and End-to-end Video Text Spotter with Transformer","created":"2021-12-09","cited_by_count":26,"area":null},{"id":"2205.01818","title":"i-Code: An Integrative and Composable Multimodal Learning Framework","created":"2022-05-03","cited_by_count":24,"area":null},{"id":"2107.12270","title":"Adaptive Hierarchical Graph Reasoning with Semantic Coherence for Video-and-Language Inference","created":"2021-07-26","cited_by_count":18,"area":null},{"id":"2302.07919","title":"COVID-VTS: Fact Extraction and Verification on Short Video Platforms","created":"2023-02-15","cited_by_count":15,"area":null},{"id":"2403.03823","title":"A Modular Approach for Multimodal Summarization of TV Shows","created":"2024-03-06","cited_by_count":13,"area":null},{"id":"2111.08774","title":"Finding the Right Moment: Human-Assisted Trailer Creation via Task Composition","created":"2021-11-16","cited_by_count":12,"area":null},{"id":"2110.07165","title":"Semantically Distributed Robust Optimization for Vision-and-Language Inference","created":"2021-10-14","cited_by_count":9,"area":null},{"id":"2406.09646","title":"A Survey of Video Datasets for Grounded Event Understanding","created":"2024-06-14","cited_by_count":9,"area":null},{"id":"2401.11654","title":"ActionHub: A Large-scale Action Video Description Dataset for Zero-shot Action Recognition","created":"2024-01-22","cited_by_count":8,"area":null},{"id":"2211.04534","title":"Going for GOAL: A Resource for Grounded Football Commentaries","created":"2022-11-08","cited_by_count":7,"area":null},{"id":"2310.14670","title":"Dataset Bias Mitigation in Multiple-Choice Visual Question Answering and Beyond","created":"2023-10-23","cited_by_count":7,"area":null},{"id":"2304.14657","title":"Knowledge Enhanced Model for Live Video Comment Generation","created":"2023-04-28","cited_by_count":6,"area":null},{"id":"2312.17429","title":"Commonsense for Zero-Shot Natural Language Video Localization","created":"2023-12-29","cited_by_count":4,"area":null},{"id":"2108.04542","title":"TrUMAn: Trope Understanding in Movies and Animations","created":"2021-08-10","cited_by_count":3,"area":null},{"id":"2201.01289","title":"Self-directed Machine Learning","created":"2022-01-04","cited_by_count":3,"area":null},{"id":"2604.08701","title":"Unified Multimodal Uncertain Inference","created":"2026-04-09","cited_by_count":3,"area":null},{"id":"2101.07632","title":"Situation and Behavior Understanding by Trope Detection on Films","created":"2021-01-19","cited_by_count":2,"area":null},{"id":"2110.06476","title":"Winning the ICCV'2021 VALUE Challenge: Task-aware Ensemble and Transfer Learning with Visual Concepts","created":"2021-10-13","cited_by_count":2,"area":null},{"id":"2210.03941","title":"Learning Fine-Grained Visual Understanding for Video Question Answering via Decoupling Spatial-Temporal Modeling","created":"2022-10-08","cited_by_count":2,"area":null},{"id":"2510.10671","title":"Image-to-Video Transfer Learning based on Image-Language Foundation Models: A Comprehensive Survey","created":"2025-10-12","cited_by_count":2,"area":null},{"id":"2203.03838","title":"Multi-Scale Self-Contrastive Learning with Hard Negative Mining for Weakly-Supervised Query-based Video Grounding","created":"2022-03-08","cited_by_count":1,"area":null},{"id":"2505.22943","title":"Can LLMs Deceive CLIP? Benchmarking Adversarial Compositionality of Pre-trained Multimodal Representation via Text Updates","created":"2025-05-28","cited_by_count":1,"area":null},{"id":"2103.15488","title":"Tracking Based Semi-Automatic Annotation for Scene Text Videos","created":"2021-03-29","cited_by_count":0,"area":null},{"id":"2106.14137","title":"Building a Video-and-Language Dataset with Human Actions for Multimodal Logical Inference","created":"2021-06-27","cited_by_count":0,"area":null},{"id":"2203.12344","title":"How Do You Do It? Fine-Grained Action Understanding with Pseudo-Adverbs","created":"2022-03-23","cited_by_count":0,"area":null},{"id":"2204.10938","title":"A Multi-level Alignment Training Scheme for Video-and-Language Grounding","created":"2022-04-22","cited_by_count":0,"area":null},{"id":"2303.05983","title":"Accountable Textual-Visual Chat Learns to Reject Human Instructions in Image Re-creation","created":"2023-03-10","cited_by_count":0,"area":null},{"id":"2309.06176","title":"Dual-Path Temporal Map Optimization for Make-up Temporal Video Grounding","created":"2023-09-12","cited_by_count":0,"area":null},{"id":"2311.16311","title":"Characterizing Video Question Answering with Sparsified Inputs","created":"2023-11-27","cited_by_count":0,"area":null},{"id":"2506.07323","title":"Speech Recognition on TV Series with Video-guided Post-ASR Correction","created":"2025-06-08","cited_by_count":0,"area":null}],"next_cursor":null}