{"list":"other","total":91,"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":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"1911.05722","title":"Momentum Contrast for Unsupervised Visual Representation Learning","created":"2019-11-13","cited_by_count":7513},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"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":"1602.07332","title":"Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations","created":"2016-02-23","cited_by_count":2656},{"id":"2109.01134","title":"Learning to Prompt for Vision-Language Models","created":"2021-09-02","cited_by_count":2281},{"id":"2107.13586","title":"Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing","created":"2021-07-28","cited_by_count":2234},{"id":"2203.12119","title":"Visual Prompt Tuning","created":"2022-03-23","cited_by_count":1681},{"id":"2104.02057","title":"An Empirical Study of Training Self-Supervised Vision Transformers","created":"2021-04-05","cited_by_count":1616},{"id":"2006.10029","title":"Big Self-Supervised Models are Strong Semi-Supervised Learners","created":"2020-06-17","cited_by_count":1380},{"id":"2104.13921","title":"Open-vocabulary Object Detection via Vision and Language Knowledge Distillation","created":"2021-04-28","cited_by_count":906},{"id":"2103.14899","title":"CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification","created":"2021-03-27","cited_by_count":806},{"id":"2201.03546","title":"Language-driven Semantic Segmentation","created":"2022-01-10","cited_by_count":717},{"id":"2210.03117","title":"MaPLe: Multi-modal Prompt Learning","created":"2022-10-06","cited_by_count":687},{"id":"1902.06162","title":"Self-supervised Visual Feature Learning with Deep Neural Networks: A Survey","created":"2019-02-16","cited_by_count":657},{"id":"2201.02605","title":"Detecting Twenty-thousand Classes using Image-level Supervision","created":"2022-01-07","cited_by_count":614},{"id":"2112.01071","title":"Extract Free Dense Labels from CLIP","created":"2021-12-02","cited_by_count":583},{"id":"2210.04150","title":"Open-Vocabulary Semantic Segmentation with Mask-adapted CLIP","created":"2022-10-09","cited_by_count":565},{"id":"2211.15654","title":"OpenScene: 3D Scene Understanding with Open Vocabularies","created":"2022-11-28","cited_by_count":559},{"id":"2202.11094","title":"GroupViT: Semantic Segmentation Emerges from Text Supervision","created":"2022-02-22","cited_by_count":531},{"id":"2112.12143","title":"Scaling Open-Vocabulary Image Segmentation with Image-Level Labels","created":"2021-12-22","cited_by_count":473},{"id":"1701.02426","title":"Scene Graph Generation by Iterative Message Passing","created":"2017-01-10","cited_by_count":462},{"id":"2011.10678","title":"Open-Vocabulary Object Detection Using Captions","created":"2020-11-20","cited_by_count":427},{"id":"1711.06640","title":"Neural Motifs: Scene Graph Parsing with Global Context","created":"2017-11-17","cited_by_count":414},{"id":"2002.11949","title":"Unbiased Scene Graph Generation from Biased Training","created":"2020-02-27","cited_by_count":356},{"id":"2306.09683","title":"Scaling Open-Vocabulary Object Detection","created":"2023-06-16","cited_by_count":343},{"id":"2210.07183","title":"Visual Classification via Description from Large Language Models","created":"2022-10-13","cited_by_count":336},{"id":"2211.11158","title":"Language in a Bottle: Language Model Guided Concept Bottlenecks for Interpretable Image Classification","created":"2022-11-21","cited_by_count":312},{"id":"2212.09561","title":"Large Language Models are Better Reasoners with Self-Verification","created":"2022-12-19","cited_by_count":307},{"id":"2212.11270","title":"Generalized Decoding for Pixel, Image, and Language","created":"2022-12-21","cited_by_count":294},{"id":"2209.03320","title":"What does a platypus look like? Generating customized prompts for zero-shot image classification","created":"2022-09-07","cited_by_count":267},{"id":"2212.05171","title":"ULIP: Learning a Unified Representation of Language, Images, and Point Clouds for 3D Understanding","created":"2022-12-10","cited_by_count":267},{"id":"1812.01880","title":"Learning to Compose Dynamic Tree Structures for Visual Contexts","created":"2018-12-05","cited_by_count":259},{"id":"2307.05300","title":"Unleashing the Emergent Cognitive Synergy in Large Language Models: A Task-Solving Agent through Multi-Persona Self-Collaboration","created":"2023-07-11","cited_by_count":251},{"id":"2112.07910","title":"Decoupling Zero-Shot Semantic Segmentation","created":"2021-12-15","cited_by_count":199},{"id":"2303.08131","title":"A Simple Framework for Open-Vocabulary Segmentation and Detection","created":"2023-03-14","cited_by_count":198},{"id":"2202.10447","title":"Transformer Quality in Linear Time","created":"2022-02-21","cited_by_count":191},{"id":"1804.04340","title":"Zero-Shot Object Detection","created":"2018-04-12","cited_by_count":189},{"id":"2211.16312","title":"PLA: Language-Driven Open-Vocabulary 3D Scene Understanding","created":"2022-11-29","cited_by_count":177},{"id":"2003.12962","title":"GPS-Net: Graph Property Sensing Network for Scene Graph Generation","created":"2020-03-29","cited_by_count":166},{"id":"2306.15880","title":"Towards Open Vocabulary Learning: A Survey","created":"2023-06-28","cited_by_count":166},{"id":"2211.14813","title":"SegCLIP: Patch Aggregation with Learnable Centers for Open-Vocabulary Semantic Segmentation","created":"2022-11-27","cited_by_count":164},{"id":"2305.14930","title":"In-Context Impersonation Reveals Large Language Models' Strengths and Biases","created":"2023-05-24","cited_by_count":155},{"id":"2303.02151","title":"Prompt, Generate, then Cache: Cascade of Foundation Models makes Strong Few-shot Learners","created":"2023-03-03","cited_by_count":152},{"id":"2112.09583","title":"Align and Prompt: Video-and-Language Pre-training with Entity Prompts","created":"2021-12-17","cited_by_count":149},{"id":"2108.00154","title":"CrossFormer: A Versatile Vision Transformer Hinging on Cross-scale Attention","created":"2021-07-31","cited_by_count":139},{"id":"2104.00308","title":"Bipartite Graph Network with Adaptive Message Passing for Unbiased Scene Graph Generation","created":"2021-04-01","cited_by_count":137},{"id":"1603.08895","title":"Latent Embeddings for Zero-shot Classification","created":"2016-03-29","cited_by_count":129},{"id":"2302.13996","title":"Aligning Bag of Regions for Open-Vocabulary Object Detection","created":"2023-02-27","cited_by_count":119},{"id":"2112.12970","title":"SGTR: End-to-end Scene Graph Generation with Transformer","created":"2021-12-24","cited_by_count":103},{"id":"2201.11460","title":"RelTR: Relation Transformer for Scene Graph Generation","created":"2022-01-27","cited_by_count":96},{"id":"2303.17225","title":"FreeSeg: Unified, Universal and Open-Vocabulary Image Segmentation","created":"2023-03-30","cited_by_count":95},{"id":"2111.12698","title":"Open-Vocabulary Instance Segmentation via Robust Cross-Modal Pseudo-Labeling","created":"2021-11-24","cited_by_count":84},{"id":"2308.03685","title":"Learning Concise and Descriptive Attributes for Visual Recognition","created":"2023-08-07","cited_by_count":73},{"id":"2111.09452","title":"Open Vocabulary Object Detection with Pseudo Bounding-Box Labels","created":"2021-11-18","cited_by_count":71},{"id":"2304.07221","title":"Instance-aware Dynamic Prompt Tuning for Pre-trained Point Cloud Models","created":"2023-04-14","cited_by_count":68},{"id":"2206.03014","title":"The Devil is in the Labels: Noisy Label Correction for Robust Scene Graph Generation","created":"2022-06-07","cited_by_count":60},{"id":"2103.16083","title":"Fully Convolutional Scene Graph Generation","created":"2021-03-30","cited_by_count":57},{"id":"2208.08165","title":"Towards Open-vocabulary Scene Graph Generation with Prompt-based Finetuning","created":"2022-08-17","cited_by_count":54},{"id":"2307.11661","title":"Enhancing CLIP with GPT-4: Harnessing Visual Descriptions as Prompts","created":"2023-07-21","cited_by_count":50},{"id":"2106.10815","title":"Structured Sparse R-CNN for Direct Scene Graph Generation","created":"2021-06-21","cited_by_count":44},{"id":"1909.02144","title":"Understanding Human Gaze Communication by Spatio-Temporal Graph Reasoning","created":"2019-09-04","cited_by_count":40},{"id":"2303.07096","title":"Prototype-based Embedding Network for Scene Graph Generation","created":"2023-03-13","cited_by_count":37},{"id":"2303.13233","title":"Visually-Prompted Language Model for Fine-Grained Scene Graph Generation in an Open World","created":"2023-03-23","cited_by_count":35},{"id":"2105.13994","title":"Linguistic Structures as Weak Supervision for Visual Scene Graph Generation","created":"2021-05-28","cited_by_count":29},{"id":"2311.10988","title":"Expanding Scene Graph Boundaries: Fully Open-vocabulary Scene Graph Generation via Visual-Concept Alignment and Retention","created":"2023-11-18","cited_by_count":29},{"id":"2001.02359","title":"Weakly Supervised Visual Semantic Parsing","created":"2020-01-08","cited_by_count":28},{"id":"2205.01297","title":"RU-Net: Regularized Unrolling Network for Scene Graph Generation","created":"2022-05-03","cited_by_count":28},{"id":"2305.12476","title":"Zero-shot Visual Relation Detection via Composite Visual Cues from Large Language Models","created":"2023-05-21","cited_by_count":27},{"id":"2103.15365","title":"Visual Distant Supervision for Scene Graph Generation","created":"2021-03-29","cited_by_count":25},{"id":"2311.09817","title":"Neural-Logic Human-Object Interaction Detection","created":"2023-11-16","cited_by_count":25},{"id":"2302.00268","title":"Compositional Prompt Tuning with Motion Cues for Open-vocabulary Video Relation Detection","created":"2023-02-01","cited_by_count":22},{"id":"2208.01834","title":"Integrating Object-aware and Interaction-aware Knowledge for Weakly Supervised Scene Graph Generation","created":"2022-08-03","cited_by_count":20},{"id":"2207.13316","title":"NICEST: Noisy Label Correction and Training for Robust Scene Graph Generation","created":"2022-07-27","cited_by_count":19},{"id":"2303.16891","title":"Mask-free OVIS: Open-Vocabulary Instance Segmentation without Manual Mask Annotations","created":"2023-03-29","cited_by_count":16},{"id":"2404.04308","title":"Visual Knowledge in the Big Model Era: Retrospect and Prospect","created":"2024-04-05","cited_by_count":16},{"id":"2308.06712","title":"Compositional Feature Augmentation for Unbiased Scene Graph Generation","created":"2023-08-13","cited_by_count":15},{"id":"2311.01755","title":"Towards a Unified Transformer-based Framework for Scene Graph Generation and Human-object Interaction Detection","created":"2023-11-03","cited_by_count":15},{"id":"2208.03763","title":"Label Semantic Knowledge Distillation for Unbiased Scene Graph Generation","created":"2022-08-07","cited_by_count":14},{"id":"2407.08133","title":"Nonverbal Interaction Detection","created":"2024-07-11","cited_by_count":14},{"id":"2311.14749","title":"Compositional Zero-shot Learning via Progressive Language-based Observations","created":"2023-11-23","cited_by_count":12},{"id":"2402.12391","title":"Toward a Team of AI-made Scientists for Scientific Discovery from Gene Expression Data","created":"2024-02-15","cited_by_count":10},{"id":"2409.10262","title":"Hydra-SGG: Hybrid Relation Assignment for One-stage Scene Graph Generation","created":"2024-09-16","cited_by_count":10},{"id":"2208.01909","title":"Rethinking the Evaluation of Unbiased Scene Graph Generation","created":"2022-08-03","cited_by_count":9},{"id":"2312.06703","title":"OpenSD: Unified Open-Vocabulary Segmentation and Detection","created":"2023-12-10","cited_by_count":7},{"id":"2404.15785","title":"Seeing Beyond Classes: Zero-Shot Grounded Situation Recognition via Language Explainer","created":"2024-04-24","cited_by_count":7},{"id":"2303.10863","title":"Decomposed Prototype Learning for Few-Shot Scene Graph Generation","created":"2023-03-20","cited_by_count":4},{"id":"2407.09191","title":"From Easy to Hard: Learning Curricular Shape-aware Features for Robust Panoptic Scene Graph Generation","created":"2024-07-12","cited_by_count":3}],"next_cursor":null}