{"total":52,"rows":[{"id":"2102.05095","title":"Is Space-Time Attention All You Need for Video Understanding?","created":"2021-02-09","cited_by_count":1620,"area":null},{"id":"2104.11227","title":"Multiscale Vision Transformers","created":"2021-04-22","cited_by_count":897,"area":null},{"id":"2112.04482","title":"FLAVA: A Foundational Language And Vision Alignment Model","created":"2021-12-08","cited_by_count":649,"area":null},{"id":"2312.03700","title":"OneLLM: One Framework to Align All Modalities with Language","created":"2023-12-06","cited_by_count":187,"area":"mllm"},{"id":"2102.09550","title":"Going Full-TILT Boogie on Document Understanding with Text-Image-Layout Transformer","created":"2021-02-18","cited_by_count":134,"area":null},{"id":"2105.04387","title":"Recent Advances in Deep Learning Based Dialogue Systems: A Systematic Survey","created":"2021-05-10","cited_by_count":130,"area":null},{"id":"2106.11013","title":"Interventional Video Grounding with Dual Contrastive Learning","created":"2021-06-21","cited_by_count":94,"area":null},{"id":"2207.12647","title":"Cross-Modal Causal Relational Reasoning for Event-Level Visual Question Answering","created":"2022-07-26","cited_by_count":57,"area":"lr"},{"id":"2104.08667","title":"SIMMC 2.0: A Task-oriented Dialog Dataset for Immersive Multimodal Conversations","created":"2021-04-18","cited_by_count":56,"area":null},{"id":"2102.13558","title":"Natural Language Video Localization: A Revisit in Span-based Question Answering Framework","created":"2021-02-26","cited_by_count":55,"area":null},{"id":"2209.09019","title":"LAVIS: A Library for Language-Vision Intelligence","created":"2022-09-15","cited_by_count":55,"area":null},{"id":"2403.04640","title":"CAT: Enhancing Multimodal Large Language Model to Answer Questions in Dynamic Audio-Visual Scenarios","created":"2024-03-07","cited_by_count":53,"area":"mllm"},{"id":"2101.12059","title":"VX2TEXT: End-to-End Learning of Video-Based Text Generation From Multimodal Inputs","created":"2021-01-28","cited_by_count":42,"area":null},{"id":"2201.08071","title":"Temporal Sentence Grounding in Videos: A Survey and Future Directions","created":"2022-01-20","cited_by_count":37,"area":null},{"id":"2202.09277","title":"(2.5+1)D Spatio-Temporal Scene Graphs for Video Question Answering","created":"2022-02-18","cited_by_count":30,"area":null},{"id":"2205.05739","title":"Learning to Retrieve Videos by Asking Questions","created":"2022-05-11","cited_by_count":18,"area":null},{"id":"2212.05765","title":"Information-Theoretic Text Hallucination Reduction for Video-grounded Dialogue","created":"2022-12-12","cited_by_count":18,"area":null},{"id":"2103.13361","title":"Structured Co-reference Graph Attention for Video-grounded Dialogue","created":"2021-03-24","cited_by_count":17,"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":"2110.06894","title":"Audio-Visual Scene-Aware Dialog and Reasoning using Audio-Visual Transformers with Joint Student-Teacher Learning","created":"2021-10-13","cited_by_count":15,"area":null},{"id":"2101.00151","title":"DVD: A Diagnostic Dataset for Multi-step Reasoning in Video Grounded Dialogue","created":"2021-01-01","cited_by_count":13,"area":null},{"id":"2312.09736","title":"HEAR: Hearing Enhanced Audio Response for Video-grounded Dialogue","created":"2023-12-15","cited_by_count":13,"area":null},{"id":"2109.01839","title":"Towards Expressive Communication with Internet Memes: A New Multimodal Conversation Dataset and Benchmark","created":"2021-09-04","cited_by_count":12,"area":null},{"id":"2205.04713","title":"Serving and Optimizing Machine Learning Workflows on Heterogeneous Infrastructures","created":"2022-05-10","cited_by_count":12,"area":null},{"id":"2103.00820","title":"Learning Reasoning Paths over Semantic Graphs for Video-grounded Dialogues","created":"2021-03-01","cited_by_count":11,"area":null},{"id":"2104.07921","title":"VGNMN: Video-grounded Neural Module Network to Video-Grounded Language Tasks","created":"2021-04-16","cited_by_count":11,"area":null},{"id":"2207.03656","title":"Video Dialog as Conversation about Objects Living in Space-Time","created":"2022-07-08","cited_by_count":11,"area":null},{"id":"2305.18969","title":"MS-DETR: Natural Language Video Localization with Sampling Moment-Moment Interaction","created":"2023-05-30","cited_by_count":8,"area":null},{"id":"2205.12502","title":"The Dialog Must Go On: Improving Visual Dialog via Generative Self-Training","created":"2022-05-25","cited_by_count":7,"area":null},{"id":"2201.01209","title":"Speech-to-SQL: Towards Speech-driven SQL Query Generation From Natural Language Question","created":"2022-01-04","cited_by_count":6,"area":null},{"id":"2206.07898","title":"Multimodal Dialogue State Tracking","created":"2022-06-16","cited_by_count":6,"area":null},{"id":"2301.01949","title":"SPRING: Situated Conversation Agent Pretrained with Multimodal Questions from Incremental Layout Graph","created":"2023-01-05","cited_by_count":6,"area":null},{"id":"2210.14512","title":"End-to-End Multimodal Representation Learning for Video Dialog","created":"2022-10-26","cited_by_count":5,"area":null},{"id":"2404.08949","title":"Multimodal Cross-Document Event Coreference Resolution Using Linear Semantic Transfer and Mixed-Modality Ensembles","created":"2024-04-13","cited_by_count":4,"area":null},{"id":"2503.19794","title":"PAVE: Patching and Adapting Video Large Language Models","created":"2025-03-25","cited_by_count":4,"area":"lr"},{"id":"2210.12460","title":"Collaborative Reasoning on Multi-Modal Semantic Graphs for Video-Grounded Dialogue Generation","created":"2022-10-22","cited_by_count":3,"area":"lr"},{"id":"2402.13146","title":"OLViT: Multi-Modal State Tracking via Attention-Based Embeddings for Video-Grounded Dialog","created":"2024-02-20","cited_by_count":3,"area":null},{"id":"2407.02218","title":"Multi-Modal Video Dialog State Tracking in the Wild","created":"2024-07-02","cited_by_count":3,"area":null},{"id":"2106.08914","title":"$C^3$: Compositional Counterfactual Contrastive Learning for Video-grounded Dialogues","created":"2021-06-16","cited_by_count":2,"area":null},{"id":"2111.03940","title":"Convolutional Gated MLP: Combining Convolutions & gMLP","created":"2021-11-06","cited_by_count":2,"area":null},{"id":"2207.00782","title":"Enabling Harmonious Human-Machine Interaction with Visual-Context Augmented Dialogue System: A Review","created":"2022-07-02","cited_by_count":2,"area":null},{"id":"2304.08083","title":"VCD: Visual Causality Discovery for Cross-Modal Question Reasoning","created":"2023-04-17","cited_by_count":2,"area":null},{"id":"2112.05328","title":"Multimodal Interactions Using Pretrained Unimodal Models for SIMMC 2.0","created":"2021-12-10","cited_by_count":1,"area":null},{"id":"2210.02526","title":"\"No, they did not\": Dialogue response dynamics in pre-trained language models","created":"2022-10-05","cited_by_count":1,"area":null},{"id":"2210.16174","title":"Multimodal Transformer for Parallel Concatenated Variational Autoencoders","created":"2022-10-28","cited_by_count":1,"area":null},{"id":"2303.08470","title":"Who's in Charge? Roles and Responsibilities of Decision-Making Components in Conversational Robots","created":"2023-03-15","cited_by_count":1,"area":null},{"id":"2305.17433","title":"A Unified Framework for Slot based Response Generation in a Multimodal Dialogue System","created":"2023-05-27","cited_by_count":1,"area":null},{"id":"2307.04907","title":"SimpleMTOD: A Simple Language Model for Multimodal Task-Oriented Dialogue with Symbolic Scene Representation","created":"2023-07-10","cited_by_count":1,"area":null},{"id":"2310.07259","title":"Uncovering Hidden Connections: Iterative Search and Reasoning for Video-grounded Dialog","created":"2023-10-11","cited_by_count":1,"area":null},{"id":"2410.05767","title":"Grounding is All You Need? Dual Temporal Grounding for Video Dialog","created":"2024-10-08","cited_by_count":1,"area":null},{"id":"2408.06725","title":"Enhancing Visual Dialog State Tracking through Iterative Object-Entity Alignment in Multi-Round Conversations","created":"2024-08-13","cited_by_count":0,"area":null},{"id":"2503.02063","title":"V$^2$Dial: Unification of Video and Visual Dialog via Multimodal Experts","created":"2025-03-03","cited_by_count":0,"area":null}],"next_cursor":null}