{"list":"other","total":69,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2309.05519","title":"NExT-GPT: Any-to-Any Multimodal LLM","created":"2023-09-11","cited_by_count":615},{"id":"1705.02101","title":"TALL: Temporal Activity Localization via Language Query","created":"2017-05-05","cited_by_count":584},{"id":"1604.01753","title":"Hollywood in Homes: Crowdsourcing Data Collection for Activity Understanding","created":"2016-04-06","cited_by_count":537},{"id":"1506.06726","title":"Skip-Thought Vectors","created":"2015-06-22","cited_by_count":322},{"id":"2004.13931","title":"Span-based Localizing Network for Natural Language Video Localization","created":"2020-04-29","cited_by_count":235},{"id":"2004.03545","title":"Dense Regression Network for Video Grounding","created":"2020-04-07","cited_by_count":176},{"id":"2501.03230","title":"Video-of-Thought: Step-by-Step Video Reasoning from Perception to Cognition","created":"2024-05-07","cited_by_count":153},{"id":"2310.18339","title":"When MOE Meets LLMs: Parameter Efficient Fine-tuning for Multi-task Medical Applications","created":"2023-10-21","cited_by_count":111},{"id":"2212.05767","title":"A Survey of Knowledge Graph Reasoning on Graph Types: Static, Dynamic, and Multimodal","created":"2022-12-12","cited_by_count":106},{"id":"2311.11810","title":"DocPedia: Unleashing the Power of Large Multimodal Model in the Frequency Domain for Versatile Document Understanding","created":"2023-11-20","cited_by_count":106},{"id":"1811.12673","title":"ComDefend: An Efficient Image Compression Model to Defend Adversarial Examples","created":"2018-11-30","cited_by_count":105},{"id":"2203.06616","title":"LAS-AT: Adversarial Training with Learnable Attack Strategy","created":"2022-03-13","cited_by_count":95},{"id":"2109.04872","title":"Negative Sample Matters: A Renaissance of Metric Learning for Temporal Grounding","created":"2021-09-10","cited_by_count":90},{"id":"1904.03282","title":"Weakly Supervised Video Moment Retrieval From Text Queries","created":"2019-04-05","cited_by_count":85},{"id":"2308.11592","title":"UniDoc: A Universal Large Multimodal Model for Simultaneous Text Detection, Recognition, Spotting and Understanding","created":"2023-08-19","cited_by_count":74},{"id":"2301.01635","title":"SPTS v2: Single-Point Scene Text Spotting","created":"2023-01-04","cited_by_count":66},{"id":"2404.12803","title":"TextSquare: Scaling up Text-Centric Visual Instruction Tuning","created":"2024-04-19","cited_by_count":62},{"id":"2008.01919","title":"Adv-watermark: A Novel Watermark Perturbation for Adversarial Examples","created":"2020-08-05","cited_by_count":56},{"id":"2407.16364","title":"Harmonizing Visual Text Comprehension and Generation","created":"2024-07-23","cited_by_count":54},{"id":"2311.13120","title":"Multi-modal In-Context Learning Makes an Ego-evolving Scene Text Recognizer","created":"2023-11-22","cited_by_count":53},{"id":"2212.01026","title":"Spectral Feature Augmentation for Graph Contrastive Learning and Beyond","created":"2022-12-02","cited_by_count":49},{"id":"2412.19806","title":"Vitron: A Unified Pixel-level Vision LLM for Understanding, Generating, Segmenting, Editing","created":"2024-10-08","cited_by_count":49},{"id":"2405.20646","title":"LLM-ESR: Large Language Models Enhancement for Long-tailed Sequential Recommendation","created":"2024-05-31","cited_by_count":47},{"id":"2008.02448","title":"Fine-grained Iterative Attention Network for TemporalLanguage Localization in Videos","created":"2020-08-06","cited_by_count":46},{"id":"2209.11572","title":"Multi-Modal Cross-Domain Alignment Network for Video Moment Retrieval","created":"2022-09-23","cited_by_count":43},{"id":"2211.10738","title":"Knowledge Graph Contrastive Learning Based on Relation-Symmetrical Structure","created":"2022-11-19","cited_by_count":43},{"id":"2303.07863","title":"You Can Ground Earlier than See: An Effective and Efficient Pipeline for Temporal Sentence Grounding in Compressed Videos","created":"2023-03-14","cited_by_count":41},{"id":"2110.05007","title":"Boosting Fast Adversarial Training with Learnable Adversarial Initialization","created":"2021-10-11","cited_by_count":40},{"id":"2408.12928","title":"ParGo: Bridging Vision-Language with Partial and Global Views","created":"2024-08-23","cited_by_count":40},{"id":"2410.05352","title":"Recent Advances of Multimodal Continual Learning: A Comprehensive Survey","created":"2024-10-07","cited_by_count":39},{"id":"2208.14882","title":"Hierarchical Local-Global Transformer for Temporal Sentence Grounding","created":"2022-08-31","cited_by_count":38},{"id":"2106.16136","title":"Weakly Supervised Temporal Adjacent Network for Language Grounding","created":"2021-06-30","cited_by_count":37},{"id":"2012.00972","title":"PWCLO-Net: Deep LiDAR Odometry in 3D Point Clouds Using Hierarchical Embedding Mask Optimization","created":"2020-12-02","cited_by_count":35},{"id":"2203.02966","title":"Exploring Optical-Flow-Guided Motion and Detection-Based Appearance for Temporal Sentence Grounding","created":"2022-03-06","cited_by_count":35},{"id":"2207.08859","title":"Prior-Guided Adversarial Initialization for Fast Adversarial Training","created":"2022-07-18","cited_by_count":35},{"id":"2308.13812","title":"Dysen-VDM: Empowering Dynamics-aware Text-to-Video Diffusion with LLMs","created":"2023-08-26","cited_by_count":35},{"id":"2303.00040","title":"Towards Generalisable Video Moment Retrieval: Visual-Dynamic Injection to Image-Text Pre-Training","created":"2023-02-28","cited_by_count":32},{"id":"2406.19255","title":"Enhancing Video-Language Representations with Structural Spatio-Temporal Alignment","created":"2024-06-27","cited_by_count":32},{"id":"2011.10254","title":"Unbalanced Incomplete Multi-view Clustering via the Scheme of View Evolution: Weak Views are Meat; Strong Views do Eat","created":"2020-11-20","cited_by_count":30},{"id":"2011.10331","title":"ANIMC: A Soft Framework for Auto-weighted Noisy and Incomplete Multi-view Clustering","created":"2020-11-20","cited_by_count":30},{"id":"2408.00555","title":"Alleviating Hallucination in Large Vision-Language Models with Active Retrieval Augmentation","created":"2024-08-01","cited_by_count":29},{"id":"2301.01871","title":"Hypotheses Tree Building for One-Shot Temporal Sentence Localization","created":"2023-01-05","cited_by_count":25},{"id":"2311.02608","title":"Deep Learning-based 3D Point Cloud Classification: A Systematic Survey and Outlook","created":"2023-11-05","cited_by_count":24},{"id":"2011.10396","title":"Double Self-weighted Multi-view Clustering via Adaptive View Fusion","created":"2020-11-20","cited_by_count":23},{"id":"2408.17150","title":"Look, Compare, Decide: Alleviating Hallucination in Large Vision-Language Models via Multi-View Multi-Path Reasoning","created":"2024-08-30","cited_by_count":23},{"id":"2003.00766","title":"Unsupervised Learning of Depth, Optical Flow and Pose with Occlusion from 3D Geometry","created":"2020-03-02","cited_by_count":21},{"id":"2410.17462","title":"Decoding Time Series with LLMs: A Multi-Agent Framework for Cross-Domain Annotation","created":"2024-10-22","cited_by_count":21},{"id":"2412.06284","title":"Your Data Is Not Perfect: Towards Cross-Domain Out-of-Distribution Detection in Class-Imbalanced Data","created":"2024-12-09","cited_by_count":21},{"id":"2411.02669","title":"Semantic-Aligned Adversarial Evolution Triangle for High-Transferability Vision-Language Attack","created":"2024-11-04","cited_by_count":18},{"id":"2102.01282","title":"Progressive Localization Networks for Language-based Moment Localization","created":"2021-02-02","cited_by_count":17},{"id":"2110.06058","title":"Multi-Modal Interaction Graph Convolutional Network for Temporal Language Localization in Videos","created":"2021-10-12","cited_by_count":16},{"id":"2304.00429","title":"Information Recovery-Driven Deep Incomplete Multiview Clustering Network","created":"2023-04-02","cited_by_count":16},{"id":"2108.06024","title":"CODEs: Chamfer Out-of-Distribution Examples against Overconfidence Issue","created":"2021-08-13","cited_by_count":14},{"id":"2308.11443","title":"Revisiting and Exploring Efficient Fast Adversarial Training via LAW: Lipschitz Regularization and Auto Weight Averaging","created":"2023-08-22","cited_by_count":14},{"id":"2012.13529","title":"Brain-inspired Search Engine Assistant based on Knowledge Graph","created":"2020-12-25","cited_by_count":13},{"id":"2311.00603","title":"Occluded Person Re-Identification with Deep Learning: A Survey and Perspectives","created":"2023-11-01","cited_by_count":13},{"id":"2012.05499","title":"Spatiotemporal Graph Neural Network based Mask Reconstruction for Video Object Segmentation","created":"2020-12-10","cited_by_count":12},{"id":"2407.13519","title":"GPSFormer: A Global Perception and Local Structure Fitting-based Transformer for Point Cloud Understanding","created":"2024-07-18","cited_by_count":12},{"id":"2409.09953","title":"Uncertainty-Guided Appearance-Motion Association Network for Out-of-Distribution Action Detection","created":"2024-09-16","cited_by_count":12},{"id":"2212.08414","title":"Deep Learning Methods for Calibrated Photometric Stereo and Beyond","created":"2022-12-16","cited_by_count":10},{"id":"2312.02207","title":"TranSegPGD: Improving Transferability of Adversarial Examples on Semantic Segmentation","created":"2023-12-03","cited_by_count":10},{"id":"2310.15444","title":"Fast Propagation is Better: Accelerating Single-Step Adversarial Training via Sampling Subnetworks","created":"2023-10-24","cited_by_count":8},{"id":"2405.04044","title":"DMOFC: Discrimination Metric-Optimized Feature Compression","created":"2024-05-07","cited_by_count":7},{"id":"2212.13163","title":"MRTNet: Multi-Resolution Temporal Network for Video Sentence Grounding","created":"2022-12-26","cited_by_count":6},{"id":"2108.00422","title":"An Effective and Robust Detector for Logo Detection","created":"2021-08-01","cited_by_count":5},{"id":"2108.10038","title":"Event Extraction by Associating Event Types and Argument Roles","created":"2021-08-23","cited_by_count":5},{"id":"2406.01601","title":"Backpropagation-Free Multi-modal On-Device Model Adaptation via Cloud-Device Collaboration","created":"2024-05-21","cited_by_count":5},{"id":"2309.03492","title":"Password-Stealing without Hacking: Wi-Fi Enabled Practical Keystroke Eavesdropping","created":"2023-09-07","cited_by_count":4}],"next_cursor":null}