{"list":"other","total":105,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"1706.06083","title":"Towards Deep Learning Models Resistant to Adversarial Attacks","created":"2017-06-19","cited_by_count":6415},{"id":"2310.03744","title":"Improved Baselines with Visual Instruction Tuning","created":"2023-10-05","cited_by_count":4418},{"id":"2201.12086","title":"BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation","created":"2022-01-28","cited_by_count":4322},{"id":"1908.02265","title":"ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks","created":"2019-08-06","cited_by_count":2222},{"id":"2305.10355","title":"Evaluating Object Hallucination in Large Vision-Language Models","created":"2023-05-17","cited_by_count":1729},{"id":"2306.13394","title":"MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models","created":"2023-06-23","cited_by_count":1652},{"id":"2107.07651","title":"Align before Fuse: Vision and Language Representation Learning with Momentum Distillation","created":"2021-07-16","cited_by_count":1619},{"id":"1505.04870","title":"Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models","created":"2015-05-19","cited_by_count":1362},{"id":"2306.00890","title":"LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day","created":"2023-06-01","cited_by_count":1305},{"id":"1412.2306","title":"Deep Visual-Semantic Alignments for Generating Image Descriptions","created":"2014-12-07","cited_by_count":968},{"id":"2306.15195","title":"Shikra: Unleashing Multimodal LLM's Referential Dialogue Magic","created":"2023-06-27","cited_by_count":906},{"id":"2310.09478","title":"MiniGPT-v2: large language model as a unified interface for vision-language multi-task learning","created":"2023-10-14","cited_by_count":625},{"id":"1710.05006","title":"Skin Lesion Analysis Toward Melanoma Detection: A Challenge at the 2017 International Symposium on Biomedical Imaging (ISBI), Hosted by the International Skin Imaging Collaboration (ISIC)","created":"2017-10-13","cited_by_count":549},{"id":"1712.09665","title":"Adversarial Patch","created":"2017-12-27","cited_by_count":517},{"id":"2004.09984","title":"BERT-ATTACK: Adversarial Attack Against BERT Using BERT","created":"2020-04-21","cited_by_count":491},{"id":"1708.00786","title":"Structure-measure: A New Way to Evaluate Foreground Maps","created":"2017-08-02","cited_by_count":480},{"id":"2207.14315","title":"SPot-the-Difference Self-Supervised Pre-training for Anomaly Detection and Segmentation","created":"2022-07-28","cited_by_count":400},{"id":"2310.00754","title":"Analyzing and Mitigating Object Hallucination in Large Vision-Language Models","created":"2023-10-01","cited_by_count":316},{"id":"1904.08653","title":"Fooling automated surveillance cameras: adversarial patches to attack person detection","created":"2019-04-18","cited_by_count":268},{"id":"1901.06706","title":"Visual Entailment: A Novel Task for Fine-Grained Image Understanding","created":"2019-01-20","cited_by_count":252},{"id":"2302.01872","title":"MOSE: A New Dataset for Video Object Segmentation in Complex Scenes","created":"2023-02-03","cited_by_count":234},{"id":"2308.08544","title":"MeViS: A Large-scale Benchmark for Video Segmentation with Motion Expressions","created":"2023-08-16","cited_by_count":228},{"id":"2306.09265","title":"LVLM-eHub: A Comprehensive Evaluation Benchmark for Large Vision-Language Models","created":"2023-06-15","cited_by_count":217},{"id":"2102.10274","title":"Concealed Object Detection","created":"2021-02-20","cited_by_count":212},{"id":"2202.10401","title":"Vision-Language Pre-Training with Triple Contrastive Learning","created":"2022-02-21","cited_by_count":212},{"id":"1605.01397","title":"Skin Lesion Analysis toward Melanoma Detection: A Challenge at the International Symposium on Biomedical Imaging (ISBI) 2016, hosted by the International Skin Imaging Collaboration (ISIC)","created":"2016-05-04","cited_by_count":198},{"id":"2308.15366","title":"AnomalyGPT: Detecting Industrial Anomalies Using Large Vision-Language Models","created":"2023-08-29","cited_by_count":171},{"id":"2202.09061","title":"VLP: A Survey on Vision-Language Pre-training","created":"2022-02-18","cited_by_count":159},{"id":"1806.02299","title":"DPatch: An Adversarial Patch Attack on Object Detectors","created":"2018-06-05","cited_by_count":147},{"id":"2311.03287","title":"Holistic Analysis of Hallucination in GPT-4V(ision): Bias and Interference Challenges","created":"2023-11-06","cited_by_count":131},{"id":"2205.10747","title":"Language Models with Image Descriptors are Strong Few-Shot Video-Language Learners","created":"2022-05-22","cited_by_count":117},{"id":"2311.12075","title":"BadCLIP: Dual-Embedding Guided Backdoor Attack on Multimodal Contrastive Learning","created":"2023-11-20","cited_by_count":115},{"id":"1811.12641","title":"Transferable Adversarial Attacks for Image and Video Object Detection","created":"2018-11-30","cited_by_count":109},{"id":"1906.01784","title":"Learning to Compose and Reason with Language Tree Structures for Visual Grounding","created":"2019-06-05","cited_by_count":98},{"id":"2003.13948","title":"Segmenting Transparent Objects in the Wild","created":"2020-03-31","cited_by_count":98},{"id":"1906.11897","title":"On Physical Adversarial Patches for Object Detection","created":"2019-06-20","cited_by_count":93},{"id":"2004.08515","title":"JL-DCF: Joint Learning and Densely-Cooperative Fusion Framework for RGB-D Salient Object Detection","created":"2020-04-18","cited_by_count":79},{"id":"2201.08970","title":"Parallel Rectangle Flip Attack: A Query-based Black-box Attack against Object Detection","created":"2022-01-22","cited_by_count":79},{"id":"2304.06022","title":"SAM Struggles in Concealed Scenes -- Empirical Study on Segment Anything","created":"2023-04-12","cited_by_count":75},{"id":"2108.08162","title":"Specificity-preserving RGB-D Saliency Detection","created":"2021-08-18","cited_by_count":70},{"id":"2008.12134","title":"Siamese Network for RGB-D Salient Object Detection and Beyond","created":"2020-08-26","cited_by_count":67},{"id":"2112.04532","title":"Segment and Complete: Defending Object Detectors against Adversarial Patch Attacks with Robust Patch Detection","created":"2021-12-08","cited_by_count":67},{"id":"2008.00217","title":"Efficient Adversarial Attacks for Visual Object Tracking","created":"2020-08-01","cited_by_count":66},{"id":"2305.16494","title":"Diffusion-Based Adversarial Sample Generation for Improved Stealthiness and Controllability","created":"2023-05-25","cited_by_count":66},{"id":"2012.12528","title":"The Translucent Patch: A Physical and Universal Attack on Object Detectors","created":"2020-12-23","cited_by_count":62},{"id":"2303.11568","title":"Large AI Models in Health Informatics: Applications, Challenges, and the Future","created":"2023-03-21","cited_by_count":61},{"id":"2302.09491","title":"X-Adv: Physical Adversarial Object Attacks against X-ray Prohibited Item Detection","created":"2023-02-19","cited_by_count":59},{"id":"2209.07790","title":"A Large-scale Multiple-objective Method for Black-box Attack against Object Detection","created":"2022-09-16","cited_by_count":55},{"id":"2404.03645","title":"Decoupling Static and Hierarchical Motion Perception for Referring Video Segmentation","created":"2024-04-04","cited_by_count":55},{"id":"2312.12436","title":"A Challenger to GPT-4V? Early Explorations of Gemini in Visual Expertise","created":"2023-12-19","cited_by_count":49},{"id":"1803.06091","title":"Salient Objects in Clutter: Bringing Salient Object Detection to the Foreground","created":"2018-03-16","cited_by_count":47},{"id":"2402.13220","title":"How Easy is It to Fool Your Multimodal LLMs? An Empirical Analysis on Deceptive Prompts","created":"2024-02-20","cited_by_count":47},{"id":"2307.12499","title":"AdvDiff: Generating Unrestricted Adversarial Examples using Diffusion Models","created":"2023-07-24","cited_by_count":46},{"id":"2111.03216","title":"Fast Camouflaged Object Detection via Edge-based Reversible Re-calibration Network","created":"2021-11-05","cited_by_count":42},{"id":"2312.15172","title":"Pre-trained Trojan Attacks for Visual Recognition","created":"2023-12-23","cited_by_count":39},{"id":"2101.10241","title":"RGB-D Salient Object Detection via 3D Convolutional Neural Networks","created":"2021-01-25","cited_by_count":36},{"id":"2304.03391","title":"Exposing and Mitigating Spurious Correlations for Cross-Modal Retrieval","created":"2023-04-06","cited_by_count":36},{"id":"1910.00068","title":"Role of Spatial Context in Adversarial Robustness for Object Detection","created":"2019-09-30","cited_by_count":35},{"id":"2306.00917","title":"Vocabulary-free Image Classification","created":"2023-06-01","cited_by_count":35},{"id":"2402.11473","title":"Poisoned Forgery Face: Towards Backdoor Attacks on Face Forgery Detection","created":"2024-02-18","cited_by_count":35},{"id":"2304.10136","title":"Diversifying the High-level Features for better Adversarial Transferability","created":"2023-04-20","cited_by_count":34},{"id":"2402.06118","title":"ViGoR: Improving Visual Grounding of Large Vision Language Models with Fine-Grained Reward Modeling","created":"2024-02-09","cited_by_count":34},{"id":"2107.01779","title":"Depth Quality-Inspired Feature Manipulation for Efficient RGB-D Salient Object Detection","created":"2021-07-05","cited_by_count":33},{"id":"2403.16257","title":"Unlearning Backdoor Threats: Enhancing Backdoor Defense in Multimodal Contrastive Learning via Local Token Unlearning","created":"2024-03-24","cited_by_count":31},{"id":"2405.16134","title":"Breaking the False Sense of Security in Backdoor Defense through Re-Activation Attack","created":"2024-05-25","cited_by_count":28},{"id":"2405.05553","title":"Towards Robust Physical-world Backdoor Attacks on Lane Detection","created":"2024-05-09","cited_by_count":26},{"id":"2403.05247","title":"Hide in Thicket: Generating Imperceptible and Rational Adversarial Perturbations on 3D Point Clouds","created":"2024-03-08","cited_by_count":24},{"id":"2010.14974","title":"Object Hider: Adversarial Patch Attack Against Object Detectors","created":"2020-10-28","cited_by_count":23},{"id":"2209.14105","title":"Exploring the Relationship between Architecture and Adversarially Robust Generalization","created":"2022-09-28","cited_by_count":23},{"id":"2311.02612","title":"GPT-4V-AD: Exploring Grounding Potential of VQA-oriented GPT-4V for Zero-shot Anomaly Detection","created":"2023-11-05","cited_by_count":23},{"id":"2311.11017","title":"Improving Adversarial Transferability by Stable Diffusion","created":"2023-11-18","cited_by_count":22},{"id":"2401.01377","title":"Does Few-shot Learning Suffer from Backdoor Attacks?","created":"2023-12-31","cited_by_count":20},{"id":"2010.04968","title":"Light Field Salient Object Detection: A Review and Benchmark","created":"2020-10-10","cited_by_count":19},{"id":"2209.09841","title":"Exploring Inconsistent Knowledge Distillation for Object Detection with Data Augmentation","created":"2022-09-20","cited_by_count":19},{"id":"2010.11679","title":"DPAttack: Diffused Patch Attacks against Universal Object Detection","created":"2020-10-16","cited_by_count":18},{"id":"2406.00934","title":"LanEvil: Benchmarking the Robustness of Lane Detection to Environmental Illusions","created":"2024-06-03","cited_by_count":18},{"id":"2209.07534","title":"Improving Robust Fairness via Balance Adversarial Training","created":"2022-09-15","cited_by_count":17},{"id":"2209.05742","title":"A Tale of HodgeRank and Spectral Method: Target Attack Against Rank Aggregation Is the Fixed Point of Adversarial Game","created":"2022-09-13","cited_by_count":16},{"id":"2311.15551","title":"Instruct2Attack: Language-Guided Semantic Adversarial Attacks","created":"2023-11-27","cited_by_count":16},{"id":"2207.07347","title":"Feasibility of Inconspicuous GAN-generated Adversarial Patches against Object Detection","created":"2022-07-15","cited_by_count":13},{"id":"1906.01452","title":"Reconstruct and Represent Video Contents for Captioning via Reinforcement Learning","created":"2019-06-03","cited_by_count":12},{"id":"2309.07398","title":"Semantic Adversarial Attacks via Diffusion Models","created":"2023-09-14","cited_by_count":12},{"id":"2405.07595","title":"Environmental Matching Attack Against Unmanned Aerial Vehicles Object Detection","created":"2024-05-13","cited_by_count":11},{"id":"2309.14327","title":"DeepSpeed-VisualChat: Multi-Round Multi-Image Interleave Chat via Multi-Modal Causal Attention","created":"2023-09-25","cited_by_count":10},{"id":"2012.13692","title":"Sparse Adversarial Attack to Object Detection","created":"2020-12-26","cited_by_count":9},{"id":"2211.15398","title":"Leveraging per Image-Token Consistency for Vision-Language Pre-training","created":"2022-11-20","cited_by_count":9},{"id":"2307.15016","title":"How Good is Google Bard's Visual Understanding? An Empirical Study on Open Challenges","created":"2023-07-27","cited_by_count":9},{"id":"2109.15177","title":"You Cannot Easily Catch Me: A Low-Detectable Adversarial Patch for Object Detectors","created":"2021-09-30","cited_by_count":8},{"id":"2305.04429","title":"Improving Cross-Task Generalization with Step-by-Step Instructions","created":"2023-05-08","cited_by_count":7}],"next_cursor":"100"}