{"list":"other","total":56,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"1701.06538","title":"Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer","created":"2017-01-23","cited_by_count":3509},{"id":"1602.07332","title":"Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations","created":"2016-02-23","cited_by_count":2656},{"id":"2006.16668","title":"GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding","created":"2020-06-30","cited_by_count":1631},{"id":"1612.06890","title":"CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning","created":"2016-12-20","cited_by_count":1457},{"id":"2408.01800","title":"MiniCPM-V: A GPT-4V Level MLLM on Your Phone","created":"2024-08-03","cited_by_count":1079},{"id":"2210.09461","title":"Token Merging: Your ViT But Faster","created":"2022-10-17","cited_by_count":1021},{"id":"2112.06905","title":"GLaM: Efficient Scaling of Language Models with Mixture-of-Experts","created":"2021-12-13","cited_by_count":897},{"id":"2406.07476","title":"VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs","created":"2024-06-11","cited_by_count":771},{"id":"2503.20215","title":"Qwen2.5-Omni Technical Report","created":"2025-03-26","cited_by_count":736},{"id":"2404.06395","title":"MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategies","created":"2024-04-09","cited_by_count":723},{"id":"1609.09430","title":"CNN Architectures for Large-Scale Audio Classification","created":"2016-09-29","cited_by_count":704},{"id":"2404.19756","title":"KAN: Kolmogorov-Arnold Networks","created":"2024-04-30","cited_by_count":649},{"id":"2509.17765","title":"Qwen3-Omni Technical Report","created":"2025-09-22","cited_by_count":497},{"id":"1906.10770","title":"Deep Modular Co-Attention Networks for Visual Question Answering","created":"2019-06-25","cited_by_count":339},{"id":"1606.00061","title":"Hierarchical Question-Image Co-Attention for Visual Question Answering","created":"2016-05-31","cited_by_count":278},{"id":"1908.08498","title":"EPIC-Fusion: Audio-Visual Temporal Binding for Egocentric Action Recognition","created":"2019-08-22","cited_by_count":226},{"id":"2203.14072","title":"Learning to Answer Questions in Dynamic Audio-Visual Scenarios","created":"2022-03-26","cited_by_count":191},{"id":"1912.04487","title":"Listen to Look: Action Recognition by Previewing Audio","created":"2019-12-10","cited_by_count":163},{"id":"2002.10698","title":"Hierarchical Conditional Relation Networks for Video Question Answering","created":"2020-02-25","cited_by_count":163},{"id":"2207.05042","title":"Audio-Visual Segmentation","created":"2022-07-11","cited_by_count":151},{"id":"1904.04357","title":"Heterogeneous Memory Enhanced Multimodal Attention Model for Video Question Answering","created":"2019-04-08","cited_by_count":146},{"id":"1901.09107","title":"Audio-Visual Scene-Aware Dialog","created":"2019-01-25","cited_by_count":123},{"id":"1812.01855","title":"Explainable and Explicit Visual Reasoning over Scene Graphs","created":"2018-12-05","cited_by_count":103},{"id":"2401.01885","title":"From Audio to Photoreal Embodiment: Synthesizing Humans in Conversations","created":"2024-01-03","cited_by_count":82},{"id":"1811.10696","title":"Attentive Relational Networks for Mapping Images to Scene Graphs","created":"2018-11-26","cited_by_count":73},{"id":"2212.07983","title":"Vision Transformers are Parameter-Efficient Audio-Visual Learners","created":"2022-12-15","cited_by_count":72},{"id":"1904.05876","title":"A Simple Baseline for Audio-Visual Scene-Aware Dialog","created":"2019-04-11","cited_by_count":52},{"id":"2303.13471","title":"Egocentric Audio-Visual Object Localization","created":"2023-03-23","cited_by_count":40},{"id":"1911.09655","title":"Temporal Reasoning via Audio Question Answering","created":"2019-11-21","cited_by_count":39},{"id":"2411.18894","title":"T2SG: Traffic Topology Scene Graph for Topology Reasoning in Autonomous Driving","created":"2024-11-28","cited_by_count":35},{"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},{"id":"2502.06910","title":"TimeKAN: KAN-based Frequency Decomposition Learning Architecture for Long-term Time Series Forecasting","created":"2025-02-10","cited_by_count":30},{"id":"2308.05421","title":"Progressive Spatio-temporal Perception for Audio-Visual Question Answering","created":"2023-08-10","cited_by_count":29},{"id":"2310.06238","title":"Tackling Data Bias in MUSIC-AVQA: Crafting a Balanced Dataset for Unbiased Question-Answering","created":"2023-10-10","cited_by_count":29},{"id":"2503.18476","title":"Global-Local Tree Search in VLMs for 3D Indoor Scene Generation","created":"2025-03-24","cited_by_count":29},{"id":"2012.14700","title":"Image-to-Image Retrieval by Learning Similarity between Scene Graphs","created":"2020-12-29","cited_by_count":23},{"id":"2501.03674","title":"Action Quality Assessment via Hierarchical Pose-guided Multi-stage Contrastive Regression","created":"2025-01-07","cited_by_count":21},{"id":"2502.12425","title":"Robust Disentangled Counterfactual Learning for Physical Audiovisual Commonsense Reasoning","created":"2025-02-18","cited_by_count":20},{"id":"2303.09706","title":"Unsupervised Self-Driving Attention Prediction via Uncertainty Mining and Knowledge Embedding","created":"2023-03-17","cited_by_count":19},{"id":"2312.12816","title":"Object-aware Adaptive-Positivity Learning for Audio-Visual Question Answering","created":"2023-12-20","cited_by_count":19},{"id":"2404.12020","title":"Look, Listen, and Answer: Overcoming Biases for Audio-Visual Question Answering","created":"2024-04-18","cited_by_count":18},{"id":"2304.08682","title":"Learning Situation Hyper-Graphs for Video Question Answering","created":"2023-04-18","cited_by_count":16},{"id":"2404.14565","title":"\"Where am I?\" Scene Retrieval with Language","created":"2024-04-22","cited_by_count":15},{"id":"2504.12080","title":"DC-SAM: In-Context Segment Anything in Images and Videos via Dual Consistency","created":"2025-04-16","cited_by_count":15},{"id":"2507.21585","title":"SafeDriveRAG: Towards Safe Autonomous Driving with Knowledge Graph-based Retrieval-Augmented Generation","created":"2025-07-29","cited_by_count":15},{"id":"2407.20693","title":"Boosting Audio Visual Question Answering via Key Semantic-Aware Cues","created":"2024-07-30","cited_by_count":14},{"id":"2412.13571","title":"PowerMLP: An Efficient Version of KAN","created":"2024-12-18","cited_by_count":14},{"id":"2110.14862","title":"Audio-visual Representation Learning for Anomaly Events Detection in Crowds","created":"2021-10-28","cited_by_count":13},{"id":"2501.05264","title":"Towards Balanced Multi-Modal Learning in 3D Human Pose Estimation","created":"2025-01-09","cited_by_count":12},{"id":"2408.01952","title":"CACE-Net: Co-guidance Attention and Contrastive Enhancement for Effective Audio-Visual Event Localization","created":"2024-08-04","cited_by_count":10},{"id":"2504.00487","title":"FortisAVQA and MAVEN: a Benchmark Dataset and Debiasing Framework for Robust Multimodal Reasoning","created":"2025-04-01","cited_by_count":8},{"id":"2405.07451","title":"CLIP-Powered TASS: Target-Aware Single-Stream Network for Audio-Visual Question Answering","created":"2024-05-13","cited_by_count":4},{"id":"2402.11875","title":"M2K-VDG: Model-Adaptive Multimodal Knowledge Anchor Enhanced Video-grounded Dialogue Generation","created":"2024-02-19","cited_by_count":3},{"id":"2504.12606","title":"Robo-SGG: Exploiting Layout-Oriented Normalization and Restitution Can Improve Robust Scene Graph Generation","created":"2025-04-17","cited_by_count":3}],"next_cursor":null}