{"list":"other","total":85,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"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":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"1905.11946","title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","created":"2019-05-28","cited_by_count":6442},{"id":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137},{"id":"1812.04948","title":"A Style-Based Generator Architecture for Generative Adversarial Networks","created":"2018-12-12","cited_by_count":6013},{"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":"2205.01068","title":"OPT: Open Pre-trained Transformer Language Models","created":"2022-05-02","cited_by_count":3512},{"id":"2109.01134","title":"Learning to Prompt for Vision-Language Models","created":"2021-09-02","cited_by_count":2281},{"id":"1411.5726","title":"CIDEr: Consensus-based Image Description Evaluation","created":"2014-11-20","cited_by_count":2046},{"id":"2203.12119","title":"Visual Prompt Tuning","created":"2022-03-23","cited_by_count":1681},{"id":"2306.02858","title":"Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding","created":"2023-06-05","cited_by_count":1471},{"id":"2308.06721","title":"IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models","created":"2023-08-13","cited_by_count":1464},{"id":"2203.05557","title":"Conditional Prompt Learning for Vision-Language Models","created":"2022-03-10","cited_by_count":1433},{"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":"1901.08971","title":"FaceForensics++: Learning to Detect Manipulated Facial Images","created":"2019-01-25","cited_by_count":1101},{"id":"2306.14824","title":"Kosmos-2: Grounding Multimodal Large Language Models to the World","created":"2023-06-26","cited_by_count":1089},{"id":"1711.09020","title":"StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation","created":"2017-11-24","cited_by_count":1039},{"id":"2306.13549","title":"A Survey on Multimodal Large Language Models","created":"2023-06-23","cited_by_count":909},{"id":"2305.06355","title":"VideoChat: Chat-Centric Video Understanding","created":"2023-05-10","cited_by_count":857},{"id":"1607.08822","title":"SPICE: Semantic Propositional Image Caption Evaluation","created":"2016-07-29","cited_by_count":824},{"id":"2210.03117","title":"MaPLe: Multi-modal Prompt Learning","created":"2022-10-06","cited_by_count":687},{"id":"2308.01390","title":"OpenFlamingo: An Open-Source Framework for Training Large Autoregressive Vision-Language Models","created":"2023-08-02","cited_by_count":565},{"id":"2007.09355","title":"Thinking in Frequency: Face Forgery Detection by Mining Frequency-aware Clues","created":"2020-07-18","cited_by_count":523},{"id":"2302.10174","title":"Towards Universal Fake Image Detectors that Generalize Across Generative Models","created":"2023-02-20","cited_by_count":490},{"id":"1912.13458","title":"Face X-ray for More General Face Forgery Detection","created":"2019-12-31","cited_by_count":470},{"id":"2307.15189","title":"Med-Flamingo: a Multimodal Medical Few-shot Learner","created":"2023-07-27","cited_by_count":392},{"id":"2204.08376","title":"Detecting Deepfakes with Self-Blended Images","created":"2022-04-18","cited_by_count":338},{"id":"2305.10415","title":"PMC-VQA: Visual Instruction Tuning for Medical Visual Question Answering","created":"2023-05-17","cited_by_count":338},{"id":"1811.00656","title":"Exposing DeepFake Videos By Detecting Face Warping Artifacts","created":"2018-11-01","cited_by_count":319},{"id":"1811.00661","title":"Exposing Deep Fakes Using Inconsistent Head Poses","created":"2018-11-01","cited_by_count":297},{"id":"2012.07657","title":"Lips Don't Lie: A Generalisable and Robust Approach to Face Forgery Detection","created":"2020-12-14","cited_by_count":287},{"id":"2310.18961","title":"AnomalyCLIP: Object-agnostic Prompt Learning for Zero-shot Anomaly Detection","created":"2023-10-29","cited_by_count":271},{"id":"1910.01717","title":"On the Detection of Digital Face Manipulation","created":"2019-10-03","cited_by_count":260},{"id":"2103.01856","title":"Spatial-Phase Shallow Learning: Rethinking Face Forgery Detection in Frequency Domain","created":"2021-03-02","cited_by_count":244},{"id":"2305.11834","title":"Pengi: An Audio Language Model for Audio Tasks","created":"2023-05-19","cited_by_count":220},{"id":"2101.01456","title":"WildDeepfake: A Challenging Real-World Dataset for Deepfake Detection","created":"2021-01-05","cited_by_count":209},{"id":"2304.13949","title":"UCF: Uncovering Common Features for Generalizable Deepfake Detection","created":"2023-04-27","cited_by_count":180},{"id":"2012.09311","title":"Learning Self-Consistency for Deepfake Detection","created":"2020-12-16","cited_by_count":179},{"id":"2402.03766","title":"MobileVLM V2: Faster and Stronger Baseline for Vision Language Model","created":"2024-02-06","cited_by_count":174},{"id":"2403.04473","title":"TextMonkey: An OCR-Free Large Multimodal Model for Understanding Document","created":"2024-03-07","cited_by_count":174},{"id":"2203.12208","title":"Self-supervised Learning of Adversarial Example: Towards Good Generalizations for Deepfake Detection","created":"2022-03-23","cited_by_count":173},{"id":"2210.06998","title":"DE-FAKE: Detection and Attribution of Fake Images Generated by Text-to-Image Generation Models","created":"2022-10-13","cited_by_count":168},{"id":"2307.02499","title":"mPLUG-DocOwl: Modularized Multimodal Large Language Model for Document Understanding","created":"2023-07-04","cited_by_count":168},{"id":"2312.00195","title":"Raising the Bar of AI-generated Image Detection with CLIP","created":"2023-11-30","cited_by_count":164},{"id":"2108.06693","title":"Exploring Temporal Coherence for More General Video Face Forgery Detection","created":"2021-08-15","cited_by_count":159},{"id":"2103.09096","title":"Frequency-aware Discriminative Feature Learning Supervised by Single-Center Loss for Face Forgery Detection","created":"2021-03-16","cited_by_count":134},{"id":"2303.17111","title":"Hierarchical Fine-Grained Image Forgery Detection and Localization","created":"2023-03-30","cited_by_count":134},{"id":"2103.10596","title":"PSCC-Net: Progressive Spatio-Channel Correlation Network for Image Manipulation Detection and Localization","created":"2021-03-19","cited_by_count":133},{"id":"2006.07397","title":"The DeepFake Detection Challenge (DFDC) Dataset","created":"2020-06-12","cited_by_count":132},{"id":"2210.14457","title":"Implicit Identity Leakage: The Stumbling Block to Improving Deepfake Detection Generalization","created":"2022-10-26","cited_by_count":123},{"id":"2104.06609","title":"Representative Forgery Mining for Fake Face Detection","created":"2021-04-14","cited_by_count":108},{"id":"2206.09541","title":"DualCoOp: Fast Adaptation to Multi-Label Recognition with Limited Annotations","created":"2022-06-20","cited_by_count":102},{"id":"2105.02577","title":"Local Relation Learning for Face Forgery Detection","created":"2021-05-06","cited_by_count":100},{"id":"2307.07494","title":"TALL: Thumbnail Layout for Deepfake Video Detection","created":"2023-07-14","cited_by_count":100},{"id":"2401.13856","title":"LAA-Net: Localized Artifact Attention Network for Quality-Agnostic and Generalizable Deepfake Detection","created":"2024-01-24","cited_by_count":89},{"id":"2103.16076","title":"Face Forensics in the Wild","created":"2021-03-30","cited_by_count":87},{"id":"2407.07035","title":"Vision-and-Language Navigation Today and Tomorrow: A Survey in the Era of Foundation Models","created":"2024-07-09","cited_by_count":79},{"id":"2307.08317","title":"AltFreezing for More General Video Face Forgery Detection","created":"2023-07-17","cited_by_count":78},{"id":"2402.00126","title":"Common Sense Reasoning for Deepfake Detection","created":"2024-01-31","cited_by_count":65},{"id":"2112.13977","title":"Exploiting Fine-grained Face Forgery Clues via Progressive Enhancement Learning","created":"2021-12-28","cited_by_count":60},{"id":"2104.04480","title":"Improving the Efficiency and Robustness of Deepfakes Detection through Precise Geometric Features","created":"2021-04-09","cited_by_count":57},{"id":"2011.09737","title":"Face Forgery Detection by 3D Decomposition","created":"2020-11-19","cited_by_count":53},{"id":"2211.11296","title":"SeeABLE: Soft Discrepancies and Bounded Contrastive Learning for Exposing Deepfakes","created":"2022-11-21","cited_by_count":49},{"id":"2404.13872","title":"FreqBlender: Enhancing DeepFake Detection by Blending Frequency Knowledge","created":"2024-04-22","cited_by_count":48},{"id":"2410.23623","title":"On Learning Multi-Modal Forgery Representation for Diffusion Generated Video Detection","created":"2024-10-31","cited_by_count":40},{"id":"2208.11148","title":"Multi-domain Learning for Updating Face Anti-spoofing Models","created":"2022-08-23","cited_by_count":39},{"id":"2207.09202","title":"Exploring Disentangled Content Information for Face Forgery Detection","created":"2022-07-19","cited_by_count":36},{"id":"2104.02156","title":"Unified Detection of Digital and Physical Face Attacks","created":"2021-04-05","cited_by_count":31},{"id":"2410.04372","title":"DiffusionFake: Enhancing Generalization in Deepfake Detection via Guided Stable Diffusion","created":"2024-10-06","cited_by_count":29},{"id":"2402.18490","title":"TAMM: TriAdapter Multi-Modal Learning for 3D Shape Understanding","created":"2024-02-28","cited_by_count":27},{"id":"2410.03878","title":"SPARTUN3D: Situated Spatial Understanding of 3D World in Large Language Models","created":"2024-10-04","cited_by_count":27},{"id":"2302.09230","title":"VLN-Trans: Translator for the Vision and Language Navigation Agent","created":"2023-02-18","cited_by_count":25},{"id":"2301.12171","title":"ZegOT: Zero-shot Segmentation Through Optimal Transport of Text Prompts","created":"2023-01-28","cited_by_count":16},{"id":"2410.23556","title":"Language-guided Hierarchical Fine-grained Image Forgery Detection and Localization","created":"2024-10-31","cited_by_count":16},{"id":"2306.02776","title":"Cheap-fake Detection with LLM using Prompt Engineering","created":"2023-06-05","cited_by_count":15},{"id":"2412.15588","title":"NeSyCoCo: A Neuro-Symbolic Concept Composer for Compositional Generalization","created":"2024-12-20","cited_by_count":13},{"id":"2402.02559","title":"NavHint: Vision and Language Navigation Agent with a Hint Generator","created":"2024-02-04","cited_by_count":12},{"id":"2403.06803","title":"Data-Independent Operator: A Training-Free Artifact Representation Extractor for Generalizable Deepfake Detection","created":"2024-03-11","cited_by_count":11},{"id":"2312.02224","title":"Tracing Hyperparameter Dependencies for Model Parsing via Learnable Graph Pooling Network","created":"2023-12-03","cited_by_count":8},{"id":"2409.10958","title":"Towards Effective User Attribution for Latent Diffusion Models via Watermark-Informed Blending","created":"2024-09-17","cited_by_count":4},{"id":"2412.18149","title":"Dense-Face: Personalized Face Generation Model via Dense Annotation Prediction","created":"2024-12-24","cited_by_count":3}],"next_cursor":null}