{"list":"other","total":59,"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":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2105.05233","title":"Diffusion Models Beat GANs on Image Synthesis","created":"2021-05-11","cited_by_count":8255},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585},{"id":"2205.11487","title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding","created":"2022-05-23","cited_by_count":6355},{"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":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"id":"2307.01952","title":"SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis","created":"2023-07-04","cited_by_count":4356},{"id":"2112.10741","title":"GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models","created":"2021-12-20","cited_by_count":3614},{"id":"2309.16609","title":"Qwen Technical Report","created":"2023-09-28","cited_by_count":3344},{"id":"2208.12242","title":"DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation","created":"2022-08-25","cited_by_count":3300},{"id":"2305.06500","title":"InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning","created":"2023-05-11","cited_by_count":2876},{"id":"2109.01134","title":"Learning to Prompt for Vision-Language Models","created":"2021-09-02","cited_by_count":2281},{"id":"2208.01618","title":"An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion","created":"2022-08-02","cited_by_count":2245},{"id":"2203.05557","title":"Conditional Prompt Learning for Vision-Language Models","created":"2022-03-10","cited_by_count":1433},{"id":"2203.03605","title":"DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection","created":"2022-03-07","cited_by_count":1319},{"id":"2212.04488","title":"Multi-Concept Customization of Text-to-Image Diffusion","created":"2022-12-08","cited_by_count":1106},{"id":"2211.01324","title":"eDiff-I: Text-to-Image Diffusion Models with an Ensemble of Expert Denoisers","created":"2022-11-02","cited_by_count":931},{"id":"2006.15055","title":"Object-Centric Learning with Slot Attention","created":"2020-06-26","cited_by_count":876},{"id":"2409.18869","title":"Emu3: Next-Token Prediction is All You Need","created":"2024-09-27","cited_by_count":781},{"id":"2408.12528","title":"Show-o: One Single Transformer to Unify Multimodal Understanding and Generation","created":"2024-08-22","cited_by_count":752},{"id":"2203.16527","title":"Exploring Plain Vision Transformer Backbones for Object Detection","created":"2022-03-30","cited_by_count":724},{"id":"2112.01071","title":"Extract Free Dense Labels from CLIP","created":"2021-12-02","cited_by_count":583},{"id":"2311.04257","title":"mPLUG-Owl2: Revolutionizing Multi-modal Large Language Model with Modality Collaboration","created":"2023-11-07","cited_by_count":547},{"id":"2112.01518","title":"DenseCLIP: Language-Guided Dense Prediction with Context-Aware Prompting","created":"2021-12-02","cited_by_count":532},{"id":"2408.11039","title":"Transfusion: Predict the Next Token and Diffuse Images with One Multi-Modal Model","created":"2024-08-20","cited_by_count":483},{"id":"2302.13848","title":"ELITE: Encoding Visual Concepts into Textual Embeddings for Customized Text-to-Image Generation","created":"2023-02-27","cited_by_count":416},{"id":"2409.04429","title":"VILA-U: a Unified Foundation Model Integrating Visual Understanding and Generation","created":"2024-09-06","cited_by_count":295},{"id":"2304.02556","title":"Detecting and Grounding Multi-Modal Media Manipulation","created":"2023-04-05","cited_by_count":99},{"id":"2307.07961","title":"EmoSet: A Large-scale Visual Emotion Dataset with Rich Attributes","created":"2023-07-16","cited_by_count":82},{"id":"2311.11860","title":"LION : Empowering Multimodal Large Language Model with Dual-Level Visual Knowledge","created":"2023-11-20","cited_by_count":81},{"id":"1605.02677","title":"Building a Large Scale Dataset for Image Emotion Recognition: The Fine Print and The Benchmark","created":"2016-05-09","cited_by_count":71},{"id":"2503.03663","title":"LION-FS: Fast & Slow Video-Language Thinker as Online Video Assistant","created":"2025-03-05","cited_by_count":58},{"id":"2309.14203","title":"Detecting and Grounding Multi-Modal Media Manipulation and Beyond","created":"2023-09-25","cited_by_count":56},{"id":"2104.00567","title":"Text to Image Generation with Semantic-Spatial Aware GAN","created":"2021-04-01","cited_by_count":53},{"id":"2106.16125","title":"Affective Image Content Analysis: Two Decades Review and New Perspectives","created":"2021-06-30","cited_by_count":47},{"id":"1509.06041","title":"Robust Image Sentiment Analysis Using Progressively Trained and Domain Transferred Deep Networks","created":"2015-09-20","cited_by_count":46},{"id":"2404.16670","title":"EmoVIT: Revolutionizing Emotion Insights with Visual Instruction Tuning","created":"2024-04-25","cited_by_count":43},{"id":"2407.20171","title":"Diffusion Feedback Helps CLIP See Better","created":"2024-07-29","cited_by_count":38},{"id":"2401.04608","title":"EmoGen: Emotional Image Content Generation with Text-to-Image Diffusion Models","created":"2024-01-09","cited_by_count":37},{"id":"1611.07145","title":"Learning Multi-level Deep Representations for Image Emotion Classification","created":"2016-11-22","cited_by_count":31},{"id":"2405.12661","title":"EmoEdit: Evoking Emotions through Image Manipulation","created":"2024-05-21","cited_by_count":30},{"id":"2203.13443","title":"MDAN: Multi-level Dependent Attention Network for Visual Emotion Analysis","created":"2022-03-25","cited_by_count":29},{"id":"1804.05287","title":"Video2Shop: Exact Matching Clothes in Videos to Online Shopping Images","created":"2018-04-14","cited_by_count":26},{"id":"2109.01812","title":"Stimuli-Aware Visual Emotion Analysis","created":"2021-09-04","cited_by_count":26},{"id":"2501.05710","title":"EmotiCrafter: Text-to-Emotional-Image Generation based on Valence-Arousal Model","created":"2025-01-10","cited_by_count":26},{"id":"2501.16297","title":"FALCON: Resolving Visual Redundancy and Fragmentation in High-resolution Multimodal Large Language Models via Visual Registers","created":"2025-01-27","cited_by_count":20},{"id":"2110.12334","title":"SOLVER: Scene-Object Interrelated Visual Emotion Reasoning Network","created":"2021-10-24","cited_by_count":18},{"id":"2409.17576","title":"ID$^3$: Identity-Preserving-yet-Diversified Diffusion Models for Synthetic Face Recognition","created":"2024-09-26","cited_by_count":18},{"id":"2507.08064","title":"PUMA: Layer-Pruned Language Model for Efficient Unified Multimodal Retrieval with Modality-Adaptive Learning","created":"2025-07-10","cited_by_count":11},{"id":"2201.10963","title":"Learning to Compose Diversified Prompts for Image Emotion Classification","created":"2022-01-26","cited_by_count":9},{"id":"2504.17224","title":"Visual and Textual Prompts in VLLMs for Enhancing Emotion Recognition","created":"2025-04-24","cited_by_count":7},{"id":"2402.00250","title":"LRDif: Diffusion Models for Under-Display Camera Emotion Recognition","created":"2024-02-01","cited_by_count":6},{"id":"2505.13419","title":"FEALLM: Advancing Facial Emotion Analysis in Multimodal Large Language Models with Emotional Synergy and Reasoning","created":"2025-05-19","cited_by_count":5}],"next_cursor":null}