{"total":44,"rows":[{"id":"2203.14072","title":"Learning to Answer Questions in Dynamic Audio-Visual Scenarios","created":"2022-03-26","cited_by_count":191,"area":null},{"id":"2111.14447","title":"ZeroCap: Zero-Shot Image-to-Text Generation for Visual-Semantic Arithmetic","created":"2021-11-29","cited_by_count":150,"area":null},{"id":"2212.07983","title":"Vision Transformers are Parameter-Efficient Audio-Visual Learners","created":"2022-12-15","cited_by_count":72,"area":null},{"id":"2208.09579","title":"Learning in Audio-visual Context: A Review, Analysis, and New Perspective","created":"2022-08-20","cited_by_count":44,"area":null},{"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":"2110.14375","title":"Perceptual Score: What Data Modalities Does Your Model Perceive?","created":"2021-10-27","cited_by_count":35,"area":null},{"id":"2403.03715","title":"MeaCap: Memory-Augmented Zero-shot Image Captioning","created":"2024-03-06","cited_by_count":35,"area":null},{"id":"2303.02437","title":"ConZIC: Controllable Zero-shot Image Captioning by Sampling-Based Polishing","created":"2023-03-04","cited_by_count":33,"area":null},{"id":"2203.04203","title":"AssistQ: Affordance-centric Question-driven Task Completion for Egocentric Assistant","created":"2022-03-08","cited_by_count":32,"area":null},{"id":"2410.11582","title":"On-the-fly Modulation for Balanced Multimodal Learning","created":"2024-10-15","cited_by_count":32,"area":null},{"id":"2311.05152","title":"Cross-modal Prompts: Adapting Large Pre-trained Models for Audio-Visual Downstream Tasks","created":"2023-11-09","cited_by_count":31,"area":null},{"id":"2308.05421","title":"Progressive Spatio-temporal Perception for Audio-Visual Question Answering","created":"2023-08-10","cited_by_count":29,"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":"2210.02884","title":"Vision+X: A Survey on Multimodal Learning in the Light of Data","created":"2022-10-05","cited_by_count":22,"area":null},{"id":"2312.12816","title":"Object-aware Adaptive-Positivity Learning for Audio-Visual Question Answering","created":"2023-12-20","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":"2305.17343","title":"Modality-Independent Teachers Meet Weakly-Supervised Audio-Visual Event Parser","created":"2023-05-27","cited_by_count":18,"area":null},{"id":"2404.12020","title":"Look, Listen, and Answer: Overcoming Biases for Audio-Visual Question Answering","created":"2024-04-18","cited_by_count":18,"area":null},{"id":"2407.20693","title":"Boosting Audio Visual Question Answering via Key Semantic-Aware Cues","created":"2024-07-30","cited_by_count":14,"area":null},{"id":"2112.04895","title":"Latent Space Explanation by Intervention","created":"2021-12-09","cited_by_count":13,"area":null},{"id":"2412.10749","title":"Patch-level Sounding Object Tracking for Audio-Visual Question Answering","created":"2024-12-14","cited_by_count":13,"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":"2110.11298","title":"Video and Text Matching with Conditioned Embeddings","created":"2021-10-21","cited_by_count":10,"area":null},{"id":"2310.16754","title":"CAD -- Contextual Multi-modal Alignment for Dynamic AVQA","created":"2023-10-25","cited_by_count":10,"area":null},{"id":"2406.06499","title":"NarrativeBridge: Enhancing Video Captioning with Causal-Temporal Narrative","created":"2024-06-10","cited_by_count":10,"area":null},{"id":"2406.09833","title":"SHMamba: Structured Hyperbolic State Space Model for Audio-Visual Question Answering","created":"2024-06-14","cited_by_count":7,"area":null},{"id":"2104.07511","title":"Ensemble of MRR and NDCG models for Visual Dialog","created":"2021-04-15","cited_by_count":5,"area":null},{"id":"2106.14069","title":"Saying the Unseen: Video Descriptions via Dialog Agents","created":"2021-06-26","cited_by_count":5,"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":"2403.06679","title":"Answering Diverse Questions via Text Attached with Key Audio-Visual Clues","created":"2024-03-11","cited_by_count":5,"area":null},{"id":"2407.16171","title":"Learning Trimodal Relation for Audio-Visual Question Answering with Missing Modality","created":"2024-07-23","cited_by_count":4,"area":null},{"id":"2402.11875","title":"M2K-VDG: Model-Adaptive Multimodal Knowledge Anchor Enhanced Video-grounded Dialogue Generation","created":"2024-02-19","cited_by_count":3,"area":null},{"id":"2510.18346","title":"AV-Master: Dual-Path Comprehensive Perception Makes Better Audio-Visual Question Answering","created":"2025-10-21","cited_by_count":3,"area":null},{"id":"2206.02761","title":"Dual Decomposition of Convex Optimization Layers for Consistent Attention in Medical Images","created":"2022-06-06","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":"2411.04933","title":"SaSR-Net: Source-Aware Semantic Representation Network for Enhancing Audio-Visual Question Answering","created":"2024-11-07","cited_by_count":2,"area":null},{"id":"2512.00115","title":"MoLT: Mixture of Layer-Wise Tokens for Efficient Audio-Visual Learning","created":"2025-11-27","cited_by_count":2,"area":null},{"id":"2601.19821","title":"Query-Guided Spatial-Temporal-Frequency Interaction for Music Audio-Visual Question Answering","created":"2026-01-27","cited_by_count":2,"area":null},{"id":"2602.04924","title":"Knowing When to Answer: Adaptive Confidence Refinement for Reliable Audio-Visual Question Answering","created":"2026-02-04","cited_by_count":2,"area":null},{"id":"2210.12112","title":"Describing Sets of Images with Textual-PCA","created":"2022-10-21","cited_by_count":1,"area":null},{"id":"2401.01637","title":"Social Media Ready Caption Generation for Brands","created":"2024-01-03","cited_by_count":0,"area":null},{"id":"2602.08309","title":"CAE-AV: Improving Audio-Visual Learning via Cross-modal Interactive Enrichment","created":"2026-02-09","cited_by_count":0,"area":null},{"id":"2603.06530","title":"AV-Unified: A Unified Framework for Audio-visual Scene Understanding","created":"2026-03-06","cited_by_count":0,"area":null},{"id":"2607.03825","title":"Q-TriM: Question-Guided Tri-Modal Attention for Audio-Visual Question Answering","created":"2026-07-04","cited_by_count":0,"area":null}],"next_cursor":null}