{"total":70,"rows":[{"id":"2102.06183","title":"Less is More: ClipBERT for Video-and-Language Learning via Sparse Sampling","created":"2021-02-11","cited_by_count":484,"area":null},{"id":"2207.06881","title":"Recurrent Memory Transformer","created":"2022-07-14","cited_by_count":203,"area":null},{"id":"2206.02146","title":"Recurrent Video Restoration Transformer with Guided Deformable Attention","created":"2022-06-05","cited_by_count":170,"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":"2201.08264","title":"End-to-end Generative Pretraining for Multimodal Video Captioning","created":"2022-01-20","cited_by_count":116,"area":null},{"id":"2107.00650","title":"CLIP-It! Language-Guided Video Summarization","created":"2021-07-01","cited_by_count":99,"area":null},{"id":"2304.11062","title":"Scaling Transformer to 1M tokens and beyond with RMT","created":"2023-04-19","cited_by_count":98,"area":null},{"id":"2503.03803","title":"EgoLife: Towards Egocentric Life Assistant","created":"2025-03-05","cited_by_count":91,"area":null},{"id":"2402.13250","title":"Video ReCap: Recursive Captioning of Hour-Long Videos","created":"2024-02-20","cited_by_count":89,"area":null},{"id":"2303.03032","title":"DeCap: Decoding CLIP Latents for Zero-Shot Captioning via Text-Only Training","created":"2023-03-06","cited_by_count":84,"area":null},{"id":"2209.06192","title":"StoryDALL-E: Adapting Pretrained Text-to-Image Transformers for Story Continuation","created":"2022-09-13","cited_by_count":74,"area":null},{"id":"2109.14910","title":"CrossCLR: Cross-modal Contrastive Learning For Multi-modal Video Representations","created":"2021-09-30","cited_by_count":72,"area":null},{"id":"2212.04979","title":"VideoCoCa: Video-Text Modeling with Zero-Shot Transfer from Contrastive Captioners","created":"2022-12-09","cited_by_count":70,"area":null},{"id":"2212.05136","title":"CLIP-TSA: CLIP-Assisted Temporal Self-Attention for Weakly-Supervised Video Anomaly Detection","created":"2022-12-09","cited_by_count":67,"area":null},{"id":"2201.05991","title":"Video Transformers: A Survey","created":"2022-01-16","cited_by_count":63,"area":null},{"id":"2209.09236","title":"Real-time Online Video Detection with Temporal Smoothing Transformers","created":"2022-09-19","cited_by_count":58,"area":null},{"id":"2110.10834","title":"Integrating Visuospatial, Linguistic and Commonsense Structure into Story Visualization","created":"2021-10-21","cited_by_count":52,"area":null},{"id":"2205.02300","title":"P3IV: Probabilistic Procedure Planning from Instructional Videos with Weak Supervision","created":"2022-05-04","cited_by_count":52,"area":null},{"id":"2105.10026","title":"Improving Generation and Evaluation of Visual Stories via Semantic Consistency","created":"2021-05-20","cited_by_count":43,"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":"2402.10790","title":"In Search of Needles in a 11M Haystack: Recurrent Memory Finds What LLMs Miss","created":"2024-02-16","cited_by_count":36,"area":null},{"id":"2303.12423","title":"Text with Knowledge Graph Augmented Transformer for Video Captioning","created":"2023-03-22","cited_by_count":28,"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":"2211.15103","title":"VLTinT: Visual-Linguistic Transformer-in-Transformer for Coherent Video Paragraph Captioning","created":"2022-11-28","cited_by_count":25,"area":null},{"id":"2105.14477","title":"Towards Diverse Paragraph Captioning for Untrimmed Videos","created":"2021-05-30","cited_by_count":22,"area":null},{"id":"2206.12972","title":"VLCap: Vision-Language with Contrastive Learning for Coherent Video Paragraph Captioning","created":"2022-06-26","cited_by_count":19,"area":null},{"id":"2303.02961","title":"Models See Hallucinations: Evaluating the Factuality in Video Captioning","created":"2023-03-06","cited_by_count":19,"area":null},{"id":"2104.04369","title":"Video-aided Unsupervised Grammar Induction","created":"2021-04-09","cited_by_count":17,"area":null},{"id":"2407.21757","title":"Learning Video Context as Interleaved Multimodal Sequences","created":"2024-07-31","cited_by_count":16,"area":null},{"id":"2207.13479","title":"AutoTransition: Learning to Recommend Video Transition Effects","created":"2022-07-27","cited_by_count":13,"area":null},{"id":"2403.03823","title":"A Modular Approach for Multimodal Summarization of TV Shows","created":"2024-03-06","cited_by_count":13,"area":null},{"id":"2210.04829","title":"Hierarchical3D Adapters for Long Video-to-text Summarization","created":"2022-10-10","cited_by_count":12,"area":null},{"id":"2207.13649","title":"Explain My Surprise: Learning Efficient Long-Term Memory by Predicting Uncertain Outcomes","created":"2022-07-27","cited_by_count":11,"area":null},{"id":"2109.02955","title":"Sensor-Augmented Egocentric-Video Captioning with Dynamic Modal Attention","created":"2021-09-07","cited_by_count":9,"area":null},{"id":"2502.20480","title":"VideoA11y: Method and Dataset for Accessible Video Description","created":"2025-02-27","cited_by_count":9,"area":null},{"id":"2303.06378","title":"Learning Grounded Vision-Language Representation for Versatile Understanding in Untrimmed Videos","created":"2023-03-11","cited_by_count":8,"area":null},{"id":"2407.09502","title":"From Text to Life: On the Reciprocal Relationship between Artificial Life and Large Language Models","created":"2024-06-14","cited_by_count":8,"area":null},{"id":"2308.07575","title":"Story Visualization by Online Text Augmentation with Context Memory","created":"2023-08-15","cited_by_count":7,"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":"2204.13001","title":"Relevance-based Margin for Contrastively-trained Video Retrieval Models","created":"2022-04-27","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":"2203.16763","title":"CREATE: A Benchmark for Chinese Short Video Retrieval and Title Generation","created":"2022-03-31","cited_by_count":5,"area":null},{"id":"2212.06206","title":"Contextual Explainable Video Representation: Human Perception-based Understanding","created":"2022-12-12","cited_by_count":5,"area":null},{"id":"2402.00976","title":"Investigating Recurrent Transformers with Dynamic Halt","created":"2024-02-01","cited_by_count":5,"area":null},{"id":"2410.19809","title":"ScreenWriter: Automatic Screenplay Generation and Movie Summarisation","created":"2024-10-17","cited_by_count":5,"area":null},{"id":"2509.18751","title":"Patch-based Memory Gate Model in Time Series Foundation Model","created":"2025-09-23","cited_by_count":4,"area":null},{"id":"2203.06356","title":"Taking an Emotional Look at Video Paragraph Captioning","created":"2022-03-12","cited_by_count":3,"area":null},{"id":"2205.03534","title":"Attract me to Buy: Advertisement Copywriting Generation with Multimodal Multi-structured Information","created":"2022-05-07","cited_by_count":3,"area":null},{"id":"2401.04881","title":"Attendre: Wait To Attend By Retrieval With Evicted Queries in Memory-Based Transformers for Long Context Processing","created":"2024-01-10","cited_by_count":3,"area":null},{"id":"2403.19221","title":"Towards Multimodal Video Paragraph Captioning Models Robust to Missing Modality","created":"2024-03-28","cited_by_count":3,"area":null},{"id":"2408.02272","title":"COM Kitchens: An Unedited Overhead-view Video Dataset as a Vision-Language Benchmark","created":"2024-08-05","cited_by_count":3,"area":null},{"id":"2503.01201","title":"Parameter-free Video Segmentation for Vision and Language Understanding","created":"2025-03-03","cited_by_count":3,"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":"2207.09083","title":"Relational Future Captioning Model for Explaining Likely Collisions in Daily Tasks","created":"2022-07-19","cited_by_count":2,"area":null},{"id":"2209.10134","title":"Recipe Generation from Unsegmented Cooking Videos","created":"2022-09-21","cited_by_count":2,"area":null},{"id":"2305.14806","title":"AWESOME: GPU Memory-constrained Long Document Summarization using Memory Mechanism and Global Salient Content","created":"2023-05-24","cited_by_count":2,"area":null},{"id":"2403.10024","title":"MR-MT3: Memory Retaining Multi-Track Music Transcription to Mitigate Instrument Leakage","created":"2024-03-15","cited_by_count":2,"area":null},{"id":"2107.14593","title":"Neural Variational Learning for Grounded Language Acquisition","created":"2021-07-20","cited_by_count":1,"area":null},{"id":"2109.06474","title":"Space Time Recurrent Memory Network","created":"2021-09-14","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":"2311.04480","title":"CLearViD: Curriculum Learning for Video Description","created":"2023-11-08","cited_by_count":1,"area":null},{"id":"2502.13034","title":"Natural Language Generation from Visual Events: State-of-the-Art and Key Open Questions","created":"2025-02-18","cited_by_count":1,"area":null},{"id":"2108.09164","title":"A Neural Conversation Generation Model via Equivalent Shared Memory Investigation","created":"2021-08-20","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":"2404.18981","title":"Decoding Radiologists' Intentions: A Novel System for Accurate Region Identification in Chest X-ray Image Analysis","created":"2024-04-29","cited_by_count":0,"area":null},{"id":"2409.00295","title":"Box2Flow: Instance-based Action Flow Graphs from Videos","created":"2024-08-30","cited_by_count":0,"area":null},{"id":"2410.09377","title":"GEM-VPC: A dual Graph-Enhanced Multimodal integration for Video Paragraph Captioning","created":"2024-10-12","cited_by_count":0,"area":null},{"id":"2504.16788","title":"Towards Explainable AI: Multi-Modal Transformer for Video-based Image Description Generation","created":"2025-04-23","cited_by_count":0,"area":null},{"id":"2507.12677","title":"Data Transformation Strategies to Remove Heterogeneity","created":"2025-07-16","cited_by_count":0,"area":null}],"next_cursor":null}