{"total":24,"rows":[{"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":"2203.01225","title":"Video Question Answering: Datasets, Algorithms and Challenges","created":"2022-03-02","cited_by_count":84,"area":null},{"id":"2104.00969","title":"TubeR: Tubelet Transformer for Video Action Detection","created":"2021-04-02","cited_by_count":55,"area":null},{"id":"2203.09773","title":"Local-Global Context Aware Transformer for Language-Guided Video Segmentation","created":"2022-03-18","cited_by_count":41,"area":null},{"id":"2105.04836","title":"Found a Reason for me? Weakly-supervised Grounded Visual Question Answering using Capsules","created":"2021-05-11","cited_by_count":22,"area":null},{"id":"2407.15047","title":"End-to-End Video Question Answering with Frame Scoring Mechanisms and Adaptive Sampling","created":"2024-07-21","cited_by_count":19,"area":null},{"id":"2109.13116","title":"VQA-MHUG: A Gaze Dataset to Study Multimodal Neural Attention in Visual Question Answering","created":"2021-09-27","cited_by_count":16,"area":null},{"id":"2304.08682","title":"Learning Situation Hyper-Graphs for Video Question Answering","created":"2023-04-18","cited_by_count":16,"area":null},{"id":"2305.02519","title":"ANetQA: A Large-scale Benchmark for Fine-grained Compositional Reasoning over Untrimmed Videos","created":"2023-05-04","cited_by_count":15,"area":null},{"id":"2305.17690","title":"HaVQA: A Dataset for Visual Question Answering and Multimodal Research in Hausa Language","created":"2023-05-28","cited_by_count":12,"area":null},{"id":"2203.14215","title":"Knowledge Mining with Scene Text for Fine-Grained Recognition","created":"2022-03-27","cited_by_count":10,"area":null},{"id":"2204.10194","title":"Semantic Structure based Query Graph Prediction for Question Answering over Knowledge Graph","created":"2022-04-15","cited_by_count":9,"area":null},{"id":"2103.14517","title":"On the hidden treasure of dialog in video question answering","created":"2021-03-26","cited_by_count":7,"area":null},{"id":"2210.16431","title":"DiMBERT: Learning Vision-Language Grounded Representations with Disentangled Multimodal-Attention","created":"2022-10-28","cited_by_count":4,"area":null},{"id":"2211.07157","title":"ParCNetV2: Oversized Kernel with Enhanced Attention","created":"2022-11-14","cited_by_count":4,"area":null},{"id":"2302.09418","title":"M-SENSE: Modeling Narrative Structure in Short Personal Narratives Using Protagonist's Mental Representations","created":"2023-02-18","cited_by_count":3,"area":null},{"id":"2307.09532","title":"Can Model Fusing Help Transformers in Long Document Classification? An Empirical Study","created":"2023-07-18","cited_by_count":3,"area":null},{"id":"2507.12823","title":"FAR-Net: Multi-Stage Fusion Network with Enhanced Semantic Alignment and Adaptive Reconciliation for Composed Image Retrieval","created":"2025-07-17","cited_by_count":3,"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":"2212.08283","title":"SceneGATE: Scene-Graph based co-Attention networks for TExt visual question answering","created":"2022-12-16","cited_by_count":2,"area":null},{"id":"2109.02370","title":"Improved RAMEN: Towards Domain Generalization for Visual Question Answering","created":"2021-09-06","cited_by_count":1,"area":null},{"id":"2406.15476","title":"Self-Regulated Data-Free Knowledge Amalgamation for Text Classification","created":"2024-06-16","cited_by_count":1,"area":null},{"id":"2602.10549","title":"Enhancing Weakly Supervised Multimodal Video Anomaly Detection through Text Guidance","created":"2026-02-11","cited_by_count":1,"area":null},{"id":"2504.02417","title":"Leveraging Static Relationships for Intra-Type and Inter-Type Message Passing in Video Question Answering","created":"2025-04-03","cited_by_count":0,"area":null}],"next_cursor":null}