{"total":73,"rows":[{"id":"2203.01225","title":"Video Question Answering: Datasets, Algorithms and Challenges","created":"2022-03-02","cited_by_count":84,"area":null},{"id":"2308.06947","title":"Knowing Where to Focus: Event-aware Transformer for Video Grounding","created":"2023-08-14","cited_by_count":79,"area":null},{"id":"2307.02869","title":"MomentDiff: Generative Video Moment Retrieval from Random to Real","created":"2023-07-06","cited_by_count":58,"area":null},{"id":"2502.07411","title":"EgoTextVQA: Towards Egocentric Scene-Text Aware Video Question Answering","created":"2025-02-11","cited_by_count":44,"area":null},{"id":"2109.06398","title":"Adaptive Proposal Generation Network for Temporal Sentence Localization in Videos","created":"2021-09-14","cited_by_count":42,"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":"2406.05615","title":"Video-Language Understanding: A Survey from Model Architecture, Model Training, and Data Perspectives","created":"2024-06-09","cited_by_count":37,"area":null},{"id":"2308.03457","title":"Cross-Silo Prototypical Calibration for Federated Learning with Non-IID Data","created":"2023-08-07","cited_by_count":35,"area":null},{"id":"2201.09168","title":"Reading-strategy Inspired Visual Representation Learning for Text-to-Video Retrieval","created":"2022-01-23","cited_by_count":34,"area":null},{"id":"2303.00040","title":"Towards Generalisable Video Moment Retrieval: Visual-Dynamic Injection to Image-Text Pre-Training","created":"2023-02-28","cited_by_count":32,"area":null},{"id":"2404.13400","title":"HiVG: Hierarchical Multimodal Fine-grained Modulation for Visual Grounding","created":"2024-04-20","cited_by_count":31,"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":"2408.16219","title":"Training-free Video Temporal Grounding using Large-scale Pre-trained Models","created":"2024-08-29","cited_by_count":28,"area":null},{"id":"2402.15070","title":"Enhancing One-Shot Federated Learning Through Data and Ensemble Co-Boosting","created":"2024-02-23","cited_by_count":27,"area":null},{"id":"2309.11131","title":"Locate and Verify: A Two-Stream Network for Improved Deepfake Detection","created":"2023-09-20","cited_by_count":26,"area":null},{"id":"2203.15227","title":"Temporal Feature Alignment and Mutual Information Maximization for Video-Based Human Pose Estimation","created":"2022-03-29","cited_by_count":24,"area":null},{"id":"2112.04222","title":"Classification-Then-Grounding: Reformulating Video Scene Graphs as Temporal Bipartite Graphs","created":"2021-12-08","cited_by_count":23,"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":"2208.12526","title":"Cross-Lingual Cross-Modal Retrieval with Noise-Robust Learning","created":"2022-08-26","cited_by_count":22,"area":null},{"id":"2109.05213","title":"Uncovering Main Causalities for Long-tailed Information Extraction","created":"2021-09-11","cited_by_count":21,"area":null},{"id":"2307.12058","title":"Discovering Spatio-Temporal Rationales for Video Question Answering","created":"2023-07-22","cited_by_count":21,"area":null},{"id":"2311.03106","title":"Unified Multi-modal Unsupervised Representation Learning for Skeleton-based Action Understanding","created":"2023-11-06","cited_by_count":20,"area":null},{"id":"2203.08013","title":"End-to-End Modeling via Information Tree for One-Shot Natural Language Spatial Video Grounding","created":"2022-03-15","cited_by_count":19,"area":null},{"id":"2210.08714","title":"Selective Query-guided Debiasing for Video Corpus Moment Retrieval","created":"2022-10-17","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":"2108.06889","title":"Causal Incremental Graph Convolution for Recommender System Retraining","created":"2021-08-16","cited_by_count":14,"area":null},{"id":"2112.00475","title":"Weakly-Supervised Video Object Grounding via Causal Intervention","created":"2021-12-01","cited_by_count":13,"area":null},{"id":"2306.02728","title":"Background-aware Moment Detection for Video Moment Retrieval","created":"2023-06-05","cited_by_count":13,"area":null},{"id":"2203.05243","title":"A Closer Look at Debiased Temporal Sentence Grounding in Videos: Dataset, Metric, and Approach","created":"2022-03-10","cited_by_count":11,"area":null},{"id":"2208.02803","title":"Semantic Data Augmentation based Distance Metric Learning for Domain Generalization","created":"2022-08-02","cited_by_count":11,"area":null},{"id":"2409.04388","title":"Question-Answering Dense Video Events","created":"2024-09-06","cited_by_count":11,"area":null},{"id":"2308.04142","title":"Class-level Structural Relation Modelling and Smoothing for Visual Representation Learning","created":"2023-08-08","cited_by_count":9,"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":"2410.07151","title":"DH-FaceVid-1K: A Large-Scale High-Quality Dataset for Face Video Generation","created":"2024-09-23","cited_by_count":9,"area":null},{"id":"2507.04599","title":"QR-LoRA: Efficient and Disentangled Fine-tuning via QR Decomposition for Customized Generation","created":"2025-07-07","cited_by_count":9,"area":null},{"id":"2503.02593","title":"CMMLoc: Advancing Text-to-PointCloud Localization with Cauchy-Mixture-Model Based Framework","created":"2025-03-04","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":"2202.09541","title":"BP-Triplet Net for Unsupervised Domain Adaptation: A Bayesian Perspective","created":"2022-02-19","cited_by_count":7,"area":null},{"id":"2208.01195","title":"Making the Best of Both Worlds: A Domain-Oriented Transformer for Unsupervised Domain Adaptation","created":"2022-08-02","cited_by_count":7,"area":null},{"id":"2208.12510","title":"PRVR: Partially Relevant Video Retrieval","created":"2022-08-26","cited_by_count":7,"area":null},{"id":"2211.11312","title":"Understanding the Vulnerability of Skeleton-based Human Activity Recognition via Black-box Attack","created":"2022-11-21","cited_by_count":7,"area":null},{"id":"2308.03267","title":"Redundancy-aware Transformer for Video Question Answering","created":"2023-08-07","cited_by_count":7,"area":null},{"id":"2401.07567","title":"Bias-Conflict Sample Synthesis and Adversarial Removal Debias Strategy for Temporal Sentence Grounding in Video","created":"2024-01-15","cited_by_count":7,"area":null},{"id":"2508.07925","title":"TAG: A Simple Yet Effective Temporal-Aware Approach for Zero-Shot Video Temporal Grounding","created":"2025-08-11","cited_by_count":7,"area":null},{"id":"2209.14046","title":"Adma-GAN: Attribute-Driven Memory Augmented GANs for Text-to-Image Generation","created":"2022-09-28","cited_by_count":6,"area":null},{"id":"2212.13163","title":"MRTNet: Multi-Resolution Temporal Network for Video Sentence Grounding","created":"2022-12-26","cited_by_count":6,"area":null},{"id":"2505.02703","title":"Structure Causal Models and LLMs Integration in Medical Visual Question Answering","created":"2025-05-05","cited_by_count":6,"area":null},{"id":"2605.29812","title":"Not All Inputs Are Valid: Towards Open-Set Video Moment Retrieval Using Language","created":"2026-05-28","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":"2504.05925","title":"SVLTA: Benchmarking Vision-Language Temporal Alignment via Synthetic Video Situation","created":"2025-04-08","cited_by_count":4,"area":null},{"id":"2507.04958","title":"Boosting Temporal Sentence Grounding via Causal Inference","created":"2025-07-07","cited_by_count":3,"area":null},{"id":"2509.01383","title":"Enhancing Partially Relevant Video Retrieval with Robust Alignment Learning","created":"2025-09-01","cited_by_count":3,"area":null},{"id":"2210.08452","title":"Efficient Cross-Modal Video Retrieval with Meta-Optimized Frames","created":"2022-10-16","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":"2109.12299","title":"A Novel Patch Convolutional Neural Network for View-based 3D Model Retrieval","created":"2021-09-25","cited_by_count":1,"area":null},{"id":"2306.04345","title":"An Overview of Challenges in Egocentric Text-Video Retrieval","created":"2023-06-07","cited_by_count":1,"area":null},{"id":"2311.06553","title":"Visual Commonsense based Heterogeneous Graph Contrastive Learning","created":"2023-11-11","cited_by_count":1,"area":null},{"id":"2311.12401","title":"CASR: Refining Action Segmentation via Marginalizing Frame-levle Causal Relationships","created":"2023-11-21","cited_by_count":1,"area":null},{"id":"2409.04699","title":"Dual-stream Feature Augmentation for Domain Generalization","created":"2024-09-07","cited_by_count":1,"area":null},{"id":"2409.16668","title":"Topic-aware Causal Intervention for Counterfactual Detection","created":"2024-09-25","cited_by_count":1,"area":null},{"id":"2510.20393","title":"Mitigating Cross-modal Representation Bias for Multicultural Image-to-Recipe Retrieval","created":"2025-10-23","cited_by_count":1,"area":null},{"id":"2605.26104","title":"EVIDENT: Routing MLLM Adaptation through Entity-Grounded Visual Evidence for Cross-Domain Video Temporal Grounding","created":"2026-05-25","cited_by_count":1,"area":null},{"id":"2607.00672","title":"DART: Difficulty-Adaptive Routing for Zero-Shot Video Temporal Grounding","created":"2026-07-01","cited_by_count":1,"area":null},{"id":"2303.02405","title":"Decision Support System for Chronic Diseases Based on Drug-Drug Interactions","created":"2023-03-04","cited_by_count":0,"area":null},{"id":"2308.04322","title":"Domain Adaptive Person Search via GAN-based Scene Synthesis for Cross-scene Videos","created":"2023-08-08","cited_by_count":0,"area":null},{"id":"2309.09311","title":"Towards Debiasing Frame Length Bias in Text-Video Retrieval via Causal Intervention","created":"2023-09-17","cited_by_count":0,"area":null},{"id":"2406.18579","title":"Hire: Hybrid-modal Interaction with Multiple Relational Enhancements for Image-Text Matching","created":"2024-06-05","cited_by_count":0,"area":null},{"id":"2407.03106","title":"Anti-Collapse Loss for Deep Metric Learning Based on Coding Rate Metric","created":"2024-07-03","cited_by_count":0,"area":null},{"id":"2508.11903","title":"OVG-HQ: Online Video Grounding with Hybrid-modal Queries","created":"2025-08-16","cited_by_count":0,"area":null},{"id":"2511.15201","title":"Towards Unbiased Cross-Modal Representation Learning for Food Image-to-Recipe Retrieval","created":"2025-11-19","cited_by_count":0,"area":null},{"id":"2603.02363","title":"Beyond Caption-Based Queries for Video Moment Retrieval","created":"2026-03-02","cited_by_count":0,"area":null},{"id":"2603.06732","title":"HERO: Hierarchical Embedding-Refinement for Open-Vocabulary Temporal Sentence Grounding in Videos","created":"2026-03-06","cited_by_count":0,"area":null}],"next_cursor":null}