{"total":19,"rows":[{"id":"2201.08264","title":"End-to-end Generative Pretraining for Multimodal Video Captioning","created":"2022-01-20","cited_by_count":116,"area":null},{"id":"2104.02026","title":"Cyclic Co-Learning of Sounding Object Visual Grounding and Sound Separation","created":"2021-04-05","cited_by_count":59,"area":null},{"id":"2307.16184","title":"UnIVAL: Unified Model for Image, Video, Audio and Language Tasks","created":"2023-07-30","cited_by_count":45,"area":null},{"id":"2204.00604","title":"Quantized GAN for Complex Music Generation from Dance Videos","created":"2022-04-01","cited_by_count":37,"area":null},{"id":"2308.11073","title":"Audio-Visual Class-Incremental Learning","created":"2023-08-21","cited_by_count":33,"area":null},{"id":"2111.05526","title":"Space-Time Memory Network for Sounding Object Localization in Videos","created":"2021-11-10","cited_by_count":10,"area":null},{"id":"2102.06448","title":"The MSR-Video to Text Dataset with Clean Annotations","created":"2021-02-12","cited_by_count":8,"area":null},{"id":"2103.14785","title":"A Comprehensive Review of the Video-to-Text Problem","created":"2021-03-27","cited_by_count":5,"area":null},{"id":"2310.02522","title":"SCB-Dataset3: A Benchmark for Detecting Student Classroom Behavior","created":"2023-10-04","cited_by_count":5,"area":null},{"id":"2401.06287","title":"Hierarchical Augmentation and Distillation for Class Incremental Audio-Visual Video Recognition","created":"2024-01-11","cited_by_count":3,"area":null},{"id":"2212.02053","title":"Day2Dark: Pseudo-Supervised Activity Recognition beyond Silent Daylight","created":"2022-12-05","cited_by_count":1,"area":null},{"id":"2303.07545","title":"Implicit and Explicit Commonsense for Multi-sentence Video Captioning","created":"2023-03-14","cited_by_count":1,"area":null},{"id":"2103.13096","title":"Repetitive Activity Counting by Sight and Sound","created":"2021-03-24","cited_by_count":0,"area":null},{"id":"2108.03329","title":"Feature-Supervised Action Modality Transfer","created":"2021-08-06","cited_by_count":0,"area":null},{"id":"2110.08872","title":"Contrastive Learning of Visual-Semantic Embeddings","created":"2021-10-17","cited_by_count":0,"area":null},{"id":"2309.09611","title":"Collaborative Three-Stream Transformers for Video Captioning","created":"2023-09-18","cited_by_count":0,"area":null},{"id":"2310.16267","title":"Student Classroom Behavior Detection based on Spatio-Temporal Network and Multi-Model Fusion","created":"2023-10-25","cited_by_count":0,"area":null},{"id":"2312.07418","title":"Attention Based Encoder Decoder Model for Video Captioning in Nepali (2023)","created":"2023-12-12","cited_by_count":0,"area":null},{"id":"2608.06930","title":"AVCap: Reinforcing Audio-Video Joint Caption with Detail-Aware Reward","created":"2026-08-07","cited_by_count":0,"area":null}],"next_cursor":null}