{"total":40,"rows":[{"id":"2112.04478","title":"Prompting Visual-Language Models for Efficient Video Understanding","created":"2021-12-08","cited_by_count":310,"area":null},{"id":"2305.18565","title":"PaLI-X: On Scaling up a Multilingual Vision and Language Model","created":"2023-05-29","cited_by_count":255,"area":null},{"id":"2407.00634","title":"Tarsier: Recipes for Training and Evaluating Large Video Description Models","created":"2024-06-30","cited_by_count":141,"area":null},{"id":"2410.03051","title":"AuroraCap: Efficient, Performant Video Detailed Captioning and a New Benchmark","created":"2024-10-04","cited_by_count":140,"area":null},{"id":"2402.13217","title":"VideoPrism: A Foundational Visual Encoder for Video Understanding","created":"2024-02-20","cited_by_count":105,"area":null},{"id":"2204.00679","title":"Learning Audio-Video Modalities from Image Captions","created":"2022-04-01","cited_by_count":80,"area":null},{"id":"2304.06708","title":"Verbs in Action: Improving verb understanding in video-language models","created":"2023-04-13","cited_by_count":76,"area":null},{"id":"2203.06667","title":"Towards Visual-Prompt Temporal Answering Grounding in Medical Instructional Video","created":"2022-03-13","cited_by_count":43,"area":null},{"id":"2106.05438","title":"Cross-Modal Discrete Representation Learning","created":"2021-06-10","cited_by_count":35,"area":null},{"id":"2303.12793","title":"CiCo: Domain-Aware Sign Language Retrieval via Cross-Lingual Contrastive Learning","created":"2023-03-22","cited_by_count":33,"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":"2307.12545","title":"Towards Video Anomaly Retrieval from Video Anomaly Detection: New Benchmarks and Model","created":"2023-07-24","cited_by_count":25,"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":"2302.11217","title":"Connecting Vision and Language with Video Localized Narratives","created":"2023-02-22","cited_by_count":24,"area":null},{"id":"2404.15955","title":"Beyond Deepfake Images: Detecting AI-Generated Videos","created":"2024-04-24","cited_by_count":22,"area":null},{"id":"2405.17927","title":"The Evolution of Multimodal Model Architectures","created":"2024-05-28","cited_by_count":21,"area":null},{"id":"2208.00061","title":"UAVM: Towards Unifying Audio and Visual Models","created":"2022-07-29","cited_by_count":20,"area":null},{"id":"2303.15616","title":"Fine-grained Audible Video Description","created":"2023-03-27","cited_by_count":18,"area":null},{"id":"2406.05629","title":"Separating the \"Chirp\" from the \"Chat\": Self-supervised Visual Grounding of Sound and Language","created":"2024-06-09","cited_by_count":17,"area":null},{"id":"2306.11729","title":"Dense Video Object Captioning from Disjoint Supervision","created":"2023-06-20","cited_by_count":10,"area":null},{"id":"2607.14935","title":"VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding","created":"2026-07-16","cited_by_count":10,"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":"2111.04823","title":"Cascaded Multilingual Audio-Visual Learning from Videos","created":"2021-11-08","cited_by_count":8,"area":null},{"id":"2202.12917","title":"Learning English with Peppa Pig","created":"2022-02-25","cited_by_count":8,"area":null},{"id":"2207.11964","title":"ConceptBeam: Concept Driven Target Speech Extraction","created":"2022-07-25","cited_by_count":8,"area":null},{"id":"2205.06253","title":"What's in a Caption? Dataset-Specific Linguistic Diversity and Its Effect on Visual Description Models and Metrics","created":"2022-05-12","cited_by_count":6,"area":null},{"id":"2209.07518","title":"Distribution Aware Metrics for Conditional Natural Language Generation","created":"2022-09-15","cited_by_count":6,"area":null},{"id":"2503.14237","title":"Make Your Training Flexible: Towards Deployment-Efficient Video Models","created":"2025-03-18","cited_by_count":6,"area":null},{"id":"2209.00277","title":"Video-Guided Curriculum Learning for Spoken Video Grounding","created":"2022-09-01","cited_by_count":5,"area":null},{"id":"2311.06231","title":"Learning Human Action Recognition Representations Without Real Humans","created":"2023-11-10","cited_by_count":5,"area":null},{"id":"2505.17423","title":"VIBE: Annotation-Free Video-to-Text Information Bottleneck Evaluation for TL;DR","created":"2025-05-23","cited_by_count":3,"area":null},{"id":"2510.14904","title":"CaptionFormer: Unified Segmentation, Tracking, and Captioning for Spatio-Temporal Objects","created":"2025-10-16","cited_by_count":3,"area":null},{"id":"2110.07575","title":"Spoken ObjectNet: A Bias-Controlled Spoken Caption Dataset","created":"2021-10-14","cited_by_count":2,"area":null},{"id":"2408.15447","title":"Fine-grained length controllable video captioning with ordinal embeddings","created":"2024-08-27","cited_by_count":2,"area":null},{"id":"2412.00049","title":"A Survey of Recent Advances and Challenges in Deep Audio-Visual Correlation Learning","created":"2024-11-24","cited_by_count":2,"area":null},{"id":"2503.18637","title":"Unbiasing through Textual Descriptions: Mitigating Representation Bias in Video Benchmarks","created":"2025-03-24","cited_by_count":2,"area":null},{"id":"2305.15692","title":"Deep Neural Networks in Video Human Action Recognition: A Review","created":"2023-05-25","cited_by_count":1,"area":null},{"id":"2202.13673","title":"Recent Advances and Challenges in Deep Audio-Visual Correlation Learning","created":"2022-02-28","cited_by_count":0,"area":null},{"id":"2406.05075","title":"Diving Deep into the Motion Representation of Video-Text Models","created":"2024-06-07","cited_by_count":0,"area":null},{"id":"2604.08762","title":"InstrAct: Towards Action-Centric Understanding in Instructional Videos","created":"2026-04-09","cited_by_count":0,"area":null}],"next_cursor":null}