{"total":35,"rows":[{"id":"2109.13238","title":"Visually Grounded Reasoning across Languages and Cultures","created":"2021-09-28","cited_by_count":189,"area":null},{"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":"2108.07154","title":"MMChat: Multi-Modal Chat Dataset on Social Media","created":"2021-08-16","cited_by_count":30,"area":null},{"id":"2203.01922","title":"Vision-Language Intelligence: Tasks, Representation Learning, and Large Models","created":"2022-03-03","cited_by_count":28,"area":null},{"id":"2311.00308","title":"From Image to Language: A Critical Analysis of Visual Question Answering (VQA) Approaches, Challenges, and Opportunities","created":"2023-11-01","cited_by_count":25,"area":null},{"id":"2105.04836","title":"Found a Reason for me? Weakly-supervised Grounded Visual Question Answering using Capsules","created":"2021-05-11","cited_by_count":22,"area":null},{"id":"2212.04119","title":"DialogCC: An Automated Pipeline for Creating High-Quality Multi-Modal Dialogue Dataset","created":"2022-12-08","cited_by_count":17,"area":null},{"id":"2109.12761","title":"OpenViDial 2.0: A Larger-Scale, Open-Domain Dialogue Generation Dataset with Visual Contexts","created":"2021-09-27","cited_by_count":16,"area":null},{"id":"2310.17914","title":"3D-Aware Visual Question Answering about Parts, Poses and Occlusions","created":"2023-10-27","cited_by_count":16,"area":null},{"id":"2104.05981","title":"CLEVR_HYP: A Challenge Dataset and Baselines for Visual Question Answering with Hypothetical Actions over Images","created":"2021-04-13","cited_by_count":14,"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":"2211.12328","title":"A survey on knowledge-enhanced multimodal learning","created":"2022-11-19","cited_by_count":11,"area":null},{"id":"2303.04634","title":"Transformer-based Image Generation from Scene Graphs","created":"2023-03-08","cited_by_count":8,"area":null},{"id":"2407.03958","title":"Stark: Social Long-Term Multi-Modal Conversation with Persona Commonsense Knowledge","created":"2024-07-04","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":"2310.14804","title":"Large Language Models can Share Images, Too!","created":"2023-10-23","cited_by_count":5,"area":null},{"id":"2308.16349","title":"Affective Visual Dialog: A Large-Scale Benchmark for Emotional Reasoning Based on Visually Grounded Conversations","created":"2023-08-30","cited_by_count":4,"area":null},{"id":"2310.16590","title":"$\\mathbb{VD}$-$\\mathbb{GR}$: Boosting $\\mathbb{V}$isual $\\mathbb{D}$ialog with Cascaded Spatial-Temporal Multi-Modal $\\mathbb{GR}$aphs","created":"2023-10-25","cited_by_count":4,"area":null},{"id":"2412.11927","title":"Transparent and Coherent Procedural Mistake Detection","created":"2024-12-16","cited_by_count":4,"area":null},{"id":"2208.10353","title":"Neuro-Symbolic Visual Dialog","created":"2022-08-22","cited_by_count":3,"area":null},{"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":"2109.09371","title":"Learning Natural Language Generation from Scratch","created":"2021-09-20","cited_by_count":2,"area":null},{"id":"2110.11881","title":"Simple Dialogue System with AUDITED","created":"2021-10-22","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":"2302.14680","title":"Which One Are You Referring To? Multimodal Object Identification in Situated Dialogue","created":"2023-02-28","cited_by_count":1,"area":null},{"id":"2410.23883","title":"'No' Matters: Out-of-Distribution Detection in Multimodality Long Dialogue","created":"2024-10-31","cited_by_count":1,"area":null},{"id":"2111.11576","title":"Building Goal-Oriented Dialogue Systems with Situated Visual Context","created":"2021-11-22","cited_by_count":0,"area":null},{"id":"2203.08362","title":"Spot the Difference: A Cooperative Object-Referring Game in Non-Perfectly Co-Observable Scene","created":"2022-03-16","cited_by_count":0,"area":null},{"id":"2211.08462","title":"Navigating Connected Memories with a Task-oriented Dialog System","created":"2022-11-15","cited_by_count":0,"area":null},{"id":"2303.05983","title":"Accountable Textual-Visual Chat Learns to Reject Human Instructions in Image Re-creation","created":"2023-03-10","cited_by_count":0,"area":null},{"id":"2402.07640","title":"Synthesizing Sentiment-Controlled Feedback For Multimodal Text and Image Data","created":"2024-02-12","cited_by_count":0,"area":null},{"id":"2502.05887","title":"MTPChat: A Multimodal Time-Aware Persona Dataset for Conversational Agents","created":"2025-02-09","cited_by_count":0,"area":null},{"id":"2509.18177","title":"A Framework for Generating Artificial Datasets to Validate Absolute and Relative Position Concepts","created":"2025-09-17","cited_by_count":0,"area":null},{"id":"2510.21761","title":"J-ORA: A Framework and Multimodal Dataset for Japanese Object Identification, Reference, Action Prediction in Robot Perception","created":"2025-10-13","cited_by_count":0,"area":null},{"id":"2605.24020","title":"Machine Intelligence that Understands Visual and Linguistic Information and Interacts with Humans and Environments","created":"2026-05-20","cited_by_count":0,"area":null}],"next_cursor":null}