{"total":34,"rows":[{"id":"2205.14100","title":"GIT: A Generative Image-to-text Transformer for Vision and Language","created":"2022-05-27","cited_by_count":537,"area":null},{"id":"2206.06488","title":"Multimodal Learning with Transformers: A Survey","created":"2022-06-13","cited_by_count":400,"area":null},{"id":"2206.08155","title":"Zero-Shot Video Question Answering via Frozen Bidirectional Language Models","created":"2022-06-16","cited_by_count":229,"area":null},{"id":"2309.00615","title":"Point-Bind & Point-LLM: Aligning Point Cloud with Multi-modality for 3D Understanding, Generation, and Instruction Following","created":"2023-09-01","cited_by_count":194,"area":null},{"id":"2201.02639","title":"MERLOT Reserve: Neural Script Knowledge through Vision and Language and Sound","created":"2022-01-07","cited_by_count":184,"area":null},{"id":"2209.15162","title":"Linearly Mapping from Image to Text Space","created":"2022-09-30","cited_by_count":142,"area":null},{"id":"2206.03428","title":"Revealing Single Frame Bias for Video-and-Language Learning","created":"2022-06-07","cited_by_count":133,"area":null},{"id":"2205.10747","title":"Language Models with Image Descriptors are Strong Few-Shot Video-Language Learners","created":"2022-05-22","cited_by_count":117,"area":null},{"id":"2106.04632","title":"VALUE: A Multi-Task Benchmark for Video-and-Language Understanding Evaluation","created":"2021-06-08","cited_by_count":95,"area":null},{"id":"2411.17040","title":"Multimodal Alignment and Fusion: A Survey","created":"2024-11-26","cited_by_count":74,"area":null},{"id":"2312.00937","title":"Zero-Shot Video Question Answering with Procedural Programs","created":"2023-12-01","cited_by_count":37,"area":null},{"id":"2205.05019","title":"Learning to Answer Visual Questions from Web Videos","created":"2022-05-10","cited_by_count":30,"area":null},{"id":"2303.14655","title":"GOAL: A Challenging Knowledge-grounded Video Captioning Benchmark for Real-time Soccer Commentary Generation","created":"2023-03-26","cited_by_count":28,"area":null},{"id":"2306.11732","title":"Retrieving-to-Answer: Zero-Shot Video Question Answering with Frozen Large Language Models","created":"2023-06-15","cited_by_count":27,"area":null},{"id":"2109.05199","title":"A Survey on Multi-modal Summarization","created":"2021-09-11","cited_by_count":26,"area":null},{"id":"2109.12776","title":"Joint Multimedia Event Extraction from Video and Article","created":"2021-09-27","cited_by_count":19,"area":null},{"id":"2205.05739","title":"Learning to Retrieve Videos by Asking Questions","created":"2022-05-11","cited_by_count":18,"area":null},{"id":"2206.02082","title":"Towards Fast Adaptation of Pretrained Contrastive Models for Multi-channel Video-Language Retrieval","created":"2022-06-05","cited_by_count":16,"area":null},{"id":"2208.00934","title":"Video Question Answering with Iterative Video-Text Co-Tokenization","created":"2022-08-01","cited_by_count":16,"area":null},{"id":"2210.15110","title":"Masked Vision-Language Transformer in Fashion","created":"2022-10-27","cited_by_count":14,"area":null},{"id":"2203.17273","title":"FindIt: Generalized Localization with Natural Language Queries","created":"2022-03-31","cited_by_count":13,"area":null},{"id":"2207.13479","title":"AutoTransition: Learning to Recommend Video Transition Effects","created":"2022-07-27","cited_by_count":13,"area":null},{"id":"2207.04858","title":"LaT: Latent Translation with Cycle-Consistency for Video-Text Retrieval","created":"2022-07-11","cited_by_count":9,"area":null},{"id":"2306.12554","title":"Improving Long-Horizon Imitation Through Instruction Prediction","created":"2023-06-21","cited_by_count":8,"area":null},{"id":"2409.19862","title":"Learning Multimodal Latent Generative Models with Energy-Based Prior","created":"2024-09-30","cited_by_count":7,"area":null},{"id":"2410.01817","title":"Aligning AI with Public Values: Deliberation and Decision-Making for Governing Multimodal LLMs in Political Video Analysis","created":"2024-09-15","cited_by_count":7,"area":null},{"id":"2304.03754","title":"Language Models are Causal Knowledge Extractors for Zero-shot Video Question Answering","created":"2023-04-07","cited_by_count":6,"area":null},{"id":"2501.14194","title":"ENTER: Event Based Interpretable Reasoning for VideoQA","created":"2025-01-24","cited_by_count":5,"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":"2111.10146","title":"DVCFlow: Modeling Information Flow Towards Human-like Video Captioning","created":"2021-11-19","cited_by_count":2,"area":null},{"id":"2606.19584","title":"Language-Instructed Vision Embeddings for Controllable and Generalizable Perception","created":"2026-06-17","cited_by_count":1,"area":null},{"id":"2209.02388","title":"Pathway to Future Symbiotic Creativity","created":"2022-08-18","cited_by_count":0,"area":null},{"id":"2301.03410","title":"In Defense of Structural Symbolic Representation for Video Event-Relation Prediction","created":"2023-01-06","cited_by_count":0,"area":null},{"id":"2312.16156","title":"From text to multimodal: a survey of adversarial example generation in question answering systems","created":"2023-12-26","cited_by_count":0,"area":null}],"next_cursor":null}