{"total":52,"rows":[{"id":"2104.08860","title":"CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval","created":"2021-04-18","cited_by_count":651,"area":null},{"id":"2101.08779","title":"AI Choreographer: Music Conditioned 3D Dance Generation with AIST++","created":"2021-01-21","cited_by_count":485,"area":null},{"id":"2106.06963","title":"Exploring and Distilling Posterior and Prior Knowledge for Radiology Report Generation","created":"2021-06-13","cited_by_count":162,"area":null},{"id":"2108.07781","title":"End-to-End Dense Video Captioning with Parallel Decoding","created":"2021-08-17","cited_by_count":133,"area":null},{"id":"2110.06615","title":"CLIP4Caption: CLIP for Video Caption","created":"2021-10-13","cited_by_count":88,"area":null},{"id":"2205.00823","title":"CenterCLIP: Token Clustering for Efficient Text-Video Retrieval","created":"2022-05-02","cited_by_count":86,"area":null},{"id":"2206.14579","title":"Competence-based Multimodal Curriculum Learning for Medical Report Generation","created":"2022-06-24","cited_by_count":76,"area":null},{"id":"2103.16775","title":"Attention, please! A survey of Neural Attention Models in Deep Learning","created":"2021-03-31","cited_by_count":51,"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":"2102.00831","title":"Semantic Grouping Network for Video Captioning","created":"2021-02-01","cited_by_count":34,"area":null},{"id":"2103.16848","title":"Embracing Uncertainty: Decoupling and De-bias for Robust Temporal Grounding","created":"2021-03-31","cited_by_count":29,"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":"2105.11087","title":"Recent Advances and Trends in Multimodal Deep Learning: A Review","created":"2021-05-24","cited_by_count":26,"area":null},{"id":"2311.07022","title":"ViLMA: A Zero-Shot Benchmark for Linguistic and Temporal Grounding in Video-Language Models","created":"2023-11-13","cited_by_count":26,"area":null},{"id":"2207.11100","title":"Zero-Shot Video Captioning with Evolving Pseudo-Tokens","created":"2022-07-22","cited_by_count":25,"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":"2112.03572","title":"Question Answering Survey: Directions, Challenges, Datasets, Evaluation Matrices","created":"2021-12-07","cited_by_count":17,"area":null},{"id":"2106.03906","title":"Learning to Guide a Saturation-Based Theorem Prover","created":"2021-06-07","cited_by_count":15,"area":null},{"id":"2304.13539","title":"Tensor Decomposition for Model Reduction in Neural Networks: A Review","created":"2023-04-26","cited_by_count":14,"area":null},{"id":"2110.09741","title":"Trajectory Prediction with Linguistic Representations","created":"2021-10-19","cited_by_count":13,"area":null},{"id":"2305.09758","title":"A Video Is Worth 4096 Tokens: Verbalize Videos To Understand Them In Zero Shot","created":"2023-05-16","cited_by_count":11,"area":null},{"id":"2412.02071","title":"Progress-Aware Video Frame Captioning","created":"2024-12-03","cited_by_count":11,"area":null},{"id":"2110.11298","title":"Video and Text Matching with Conditioned Embeddings","created":"2021-10-21","cited_by_count":10,"area":null},{"id":"2112.01073","title":"Controllable Video Captioning with an Exemplar Sentence","created":"2021-12-02","cited_by_count":9,"area":null},{"id":"2304.03147","title":"Improving Visual Question Answering Models through Robustness Analysis and In-Context Learning with a Chain of Basic Questions","created":"2023-04-06","cited_by_count":9,"area":null},{"id":"2405.11483","title":"MICap: A Unified Model for Identity-aware Movie Descriptions","created":"2024-05-19","cited_by_count":9,"area":null},{"id":"2104.05758","title":"Towards Extremely Compact RNNs for Video Recognition with Fully Decomposed Hierarchical Tucker Structure","created":"2021-04-12","cited_by_count":8,"area":null},{"id":"2104.00285","title":"CUPID: Adaptive Curation of Pre-training Data for Video-and-Language Representation Learning","created":"2021-04-01","cited_by_count":6,"area":null},{"id":"2311.07285","title":"Multi Sentence Description of Complex Manipulation Action Videos","created":"2023-11-13","cited_by_count":6,"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":"2112.13050","title":"Self-Gated Memory Recurrent Network for Efficient Scalable HDR Deghosting","created":"2021-12-24","cited_by_count":5,"area":null},{"id":"2108.02147","title":"Optimizing Latency for Online Video CaptioningUsing Audio-Visual Transformers","created":"2021-08-04","cited_by_count":3,"area":null},{"id":"2204.05976","title":"Video Captioning: a comparative review of where we are and which could be the route","created":"2022-04-12","cited_by_count":3,"area":null},{"id":"2210.16644","title":"Unsupervised Audio-Visual Lecture Segmentation","created":"2022-10-29","cited_by_count":3,"area":null},{"id":"2305.01928","title":"Visual Transformation Telling","created":"2023-05-03","cited_by_count":3,"area":null},{"id":"2503.24096","title":"DANTE-AD: Dual-Vision Attention Network for Long-Term Audio Description","created":"2025-03-31","cited_by_count":3,"area":null},{"id":"2107.11707","title":"Boosting Video Captioning with Dynamic Loss Network","created":"2021-07-25","cited_by_count":2,"area":null},{"id":"2111.10146","title":"DVCFlow: Modeling Information Flow Towards Human-like Video Captioning","created":"2021-11-19","cited_by_count":2,"area":null},{"id":"2201.06207","title":"Discourse Analysis for Evaluating Coherence in Video Paragraph Captions","created":"2022-01-17","cited_by_count":2,"area":null},{"id":"2307.01969","title":"Multimodal Prompt Learning for Product Title Generation with Extremely Limited Labels","created":"2023-07-05","cited_by_count":2,"area":null},{"id":"2202.10828","title":"Exploiting long-term temporal dynamics for video captioning","created":"2022-02-22","cited_by_count":1,"area":null},{"id":"2205.08356","title":"DouFu: A Double Fusion Joint Learning Method For Driving Trajectory Representation","created":"2022-05-05","cited_by_count":1,"area":null},{"id":"2212.10690","title":"METEOR Guided Divergence for Video Captioning","created":"2022-12-20","cited_by_count":1,"area":null},{"id":"2311.04480","title":"CLearViD: Curriculum Learning for Video Description","created":"2023-11-08","cited_by_count":1,"area":null},{"id":"2506.20583","title":"Dense Video Captioning using Graph-based Sentence Summarization","created":"2025-06-25","cited_by_count":1,"area":null},{"id":"2107.09285","title":"Neural Abstructions: Abstractions that Support Construction for Grounded Language Learning","created":"2021-07-20","cited_by_count":0,"area":null},{"id":"2211.02982","title":"Event and Entity Extraction from Generated Video Captions","created":"2022-11-05","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":"2312.12721","title":"Cross-Modal Reasoning with Event Correlation for Video Question Answering","created":"2023-12-20","cited_by_count":0,"area":null},{"id":"2410.16624","title":"EVC-MF: End-to-end Video Captioning Network with Multi-scale Features","created":"2024-10-22","cited_by_count":0,"area":null},{"id":"2410.23988","title":"JEMA: A Joint Embedding Framework for Scalable Co-Learning with Multimodal Alignment","created":"2024-10-31","cited_by_count":0,"area":null},{"id":"2506.20567","title":"Show, Tell and Summarize: Dense Video Captioning Using Visual Cue Aided Sentence Summarization","created":"2025-06-25","cited_by_count":0,"area":null}],"next_cursor":null}