{"total":176,"rows":[{"id":"2102.03334","title":"ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision","created":"2021-02-05","cited_by_count":1230,"area":null},{"id":"2102.08981","title":"Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Concepts","created":"2021-02-17","cited_by_count":1216,"area":null},{"id":"2112.03857","title":"Grounded Language-Image Pre-training","created":"2021-12-07","cited_by_count":1156,"area":null},{"id":"2103.03206","title":"Perceiver: General Perception with Iterative Attention","created":"2021-03-04","cited_by_count":1104,"area":null},{"id":"2104.12763","title":"MDETR -- Modulated Detection for End-to-End Multi-Modal Understanding","created":"2021-04-26","cited_by_count":819,"area":null},{"id":"2202.11094","title":"GroupViT: Semantic Segmentation Emerges from Text Supervision","created":"2022-02-22","cited_by_count":531,"area":null},{"id":"2102.06183","title":"Less is More: ClipBERT for Video-and-Language Learning via Sparse Sampling","created":"2021-02-11","cited_by_count":484,"area":null},{"id":"2104.12756","title":"InfographicVQA","created":"2021-04-26","cited_by_count":437,"area":null},{"id":"2106.02636","title":"MERLOT: Multimodal Neural Script Knowledge Models","created":"2021-06-04","cited_by_count":311,"area":null},{"id":"2103.01913","title":"WIT: Wikipedia-based Image Text Dataset for Multimodal Multilingual Machine Learning","created":"2021-03-02","cited_by_count":287,"area":null},{"id":"2206.05836","title":"GLIPv2: Unifying Localization and Vision-Language Understanding","created":"2022-06-12","cited_by_count":275,"area":null},{"id":"2103.14586","title":"Understanding Robustness of Transformers for Image Classification","created":"2021-03-26","cited_by_count":249,"area":null},{"id":"2103.15358","title":"Multi-Scale Vision Longformer: A New Vision Transformer for High-Resolution Image Encoding","created":"2021-03-29","cited_by_count":207,"area":null},{"id":"2111.11431","title":"RedCaps: web-curated image-text data created by the people, for the people","created":"2021-11-22","cited_by_count":180,"area":null},{"id":"2104.06039","title":"MultiModalQA: Complex Question Answering over Text, Tables and Images","created":"2021-04-13","cited_by_count":179,"area":null},{"id":"2204.11817","title":"Translation between Molecules and Natural Language","created":"2022-04-25","cited_by_count":177,"area":null},{"id":"2210.06044","title":"Multi-Granularity Cross-modal Alignment for Generalized Medical Visual Representation Learning","created":"2022-10-12","cited_by_count":159,"area":null},{"id":"2302.03084","title":"Pic2Word: Mapping Pictures to Words for Zero-shot Composed Image Retrieval","created":"2023-02-06","cited_by_count":156,"area":null},{"id":"2101.11272","title":"VisualMRC: Machine Reading Comprehension on Document Images","created":"2021-01-27","cited_by_count":151,"area":null},{"id":"2111.14447","title":"ZeroCap: Zero-Shot Image-to-Text Generation for Visual-Semantic Arithmetic","created":"2021-11-29","cited_by_count":150,"area":null},{"id":"2106.09785","title":"Efficient Self-supervised Vision Transformers for Representation Learning","created":"2021-06-17","cited_by_count":149,"area":null},{"id":"2206.03428","title":"Revealing Single Frame Bias for Video-and-Language Learning","created":"2022-06-07","cited_by_count":133,"area":null},{"id":"2210.13452","title":"MetaFormer Baselines for Vision","created":"2022-10-24","cited_by_count":132,"area":null},{"id":"2105.04387","title":"Recent Advances in Deep Learning Based Dialogue Systems: A Systematic Survey","created":"2021-05-10","cited_by_count":130,"area":null},{"id":"2211.09699","title":"PromptCap: Prompt-Guided Task-Aware Image Captioning","created":"2022-11-15","cited_by_count":104,"area":null},{"id":"2308.07026","title":"AdvCLIP: Downstream-agnostic Adversarial Examples in Multimodal Contrastive Learning","created":"2023-08-14","cited_by_count":103,"area":null},{"id":"2103.16553","title":"Thinking Fast and Slow: Efficient Text-to-Visual Retrieval with Transformers","created":"2021-03-30","cited_by_count":93,"area":null},{"id":"2204.02968","title":"Temporal Alignment Networks for Long-term Video","created":"2022-04-06","cited_by_count":84,"area":null},{"id":"2202.05786","title":"Multi-Modal Knowledge Graph Construction and Application: A Survey","created":"2022-02-11","cited_by_count":74,"area":null},{"id":"2112.12494","title":"LaTr: Layout-Aware Transformer for Scene-Text VQA","created":"2021-12-23","cited_by_count":72,"area":null},{"id":"2206.09059","title":"CLiMB: A Continual Learning Benchmark for Vision-and-Language Tasks","created":"2022-06-18","cited_by_count":68,"area":null},{"id":"2111.13579","title":"VL-LTR: Learning Class-wise Visual-Linguistic Representation for Long-Tailed Visual Recognition","created":"2021-11-26","cited_by_count":65,"area":null},{"id":"2205.01883","title":"All You May Need for VQA are Image Captions","created":"2022-05-04","cited_by_count":65,"area":null},{"id":"2207.09248","title":"Don't Stop Learning: Towards Continual Learning for the CLIP Model","created":"2022-07-19","cited_by_count":61,"area":null},{"id":"2307.11545","title":"Bridging Vision and Language Encoders: Parameter-Efficient Tuning for Referring Image Segmentation","created":"2023-07-21","cited_by_count":61,"area":null},{"id":"2104.08666","title":"Worst of Both Worlds: Biases Compound in Pre-trained Vision-and-Language Models","created":"2021-04-18","cited_by_count":52,"area":null},{"id":"2304.14933","title":"An Empirical Study of Multimodal Model Merging","created":"2023-04-28","cited_by_count":52,"area":null},{"id":"2312.04089","title":"Open-Vocabulary Segmentation with Semantic-Assisted Calibration","created":"2023-12-07","cited_by_count":49,"area":null},{"id":"2105.07878","title":"A Review on Explainability in Multimodal Deep Neural Nets","created":"2021-05-17","cited_by_count":46,"area":null},{"id":"2202.02317","title":"Webly Supervised Concept Expansion for General Purpose Vision Models","created":"2022-02-04","cited_by_count":45,"area":null},{"id":"2112.15283","title":"ERNIE-ViLG: Unified Generative Pre-training for Bidirectional Vision-Language Generation","created":"2021-12-31","cited_by_count":41,"area":null},{"id":"2203.09773","title":"Local-Global Context Aware Transformer for Language-Guided Video Segmentation","created":"2022-03-18","cited_by_count":41,"area":null},{"id":"2210.07179","title":"MAPL: Parameter-Efficient Adaptation of Unimodal Pre-Trained Models for Vision-Language Few-Shot Prompting","created":"2022-10-13","cited_by_count":41,"area":null},{"id":"2203.15588","title":"Deep Multi-modal Fusion of Image and Non-image Data in Disease Diagnosis and Prognosis: A Review","created":"2022-03-25","cited_by_count":37,"area":null},{"id":"2105.14211","title":"M6-UFC: Unifying Multi-Modal Controls for Conditional Image Synthesis via Non-Autoregressive Generative Transformers","created":"2021-05-29","cited_by_count":36,"area":null},{"id":"2210.08901","title":"Contrastive Language-Image Pre-Training with Knowledge Graphs","created":"2022-10-17","cited_by_count":34,"area":null},{"id":"2207.01887","title":"Open-Vocabulary Multi-Label Classification via Multi-Modal Knowledge Transfer","created":"2022-07-05","cited_by_count":33,"area":null},{"id":"2207.12661","title":"Learning Visual Representation from Modality-Shared Contrastive Language-Image Pre-training","created":"2022-07-26","cited_by_count":32,"area":null},{"id":"2203.01922","title":"Vision-Language Intelligence: Tasks, Representation Learning, and Large Models","created":"2022-03-03","cited_by_count":28,"area":null},{"id":"2212.01769","title":"CoupAlign: Coupling Word-Pixel with Sentence-Mask Alignments for Referring Image Segmentation","created":"2022-12-04","cited_by_count":28,"area":null},{"id":"2303.12423","title":"Text with Knowledge Graph Augmented Transformer for Video Captioning","created":"2023-03-22","cited_by_count":28,"area":null},{"id":"2209.05534","title":"PreSTU: Pre-Training for Scene-Text Understanding","created":"2022-09-12","cited_by_count":27,"area":null},{"id":"2107.08685","title":"Constructing Multi-Modal Dialogue Dataset by Replacing Text with Semantically Relevant Images","created":"2021-07-19","cited_by_count":26,"area":null},{"id":"2211.09778","title":"I Can't Believe There's No Images! Learning Visual Tasks Using only Language Supervision","created":"2022-11-17","cited_by_count":26,"area":null},{"id":"2106.05251","title":"Bayesian Attention Belief Networks","created":"2021-06-09","cited_by_count":25,"area":null},{"id":"2202.07247","title":"CommerceMM: Large-Scale Commerce MultiModal Representation Learning with Omni Retrieval","created":"2022-02-15","cited_by_count":25,"area":null},{"id":"2101.06013","title":"Reasoning over Vision and Language: Exploring the Benefits of Supplemental Knowledge","created":"2021-01-15","cited_by_count":24,"area":null},{"id":"2211.15516","title":"DQ-DETR: Dual Query Detection Transformer for Phrase Extraction and Grounding","created":"2022-11-28","cited_by_count":24,"area":null},{"id":"2205.11728","title":"ItemSage: Learning Product Embeddings for Shopping Recommendations at Pinterest","created":"2022-05-24","cited_by_count":23,"area":null},{"id":"2209.14156","title":"TVLT: Textless Vision-Language Transformer","created":"2022-09-28","cited_by_count":22,"area":null},{"id":"2211.11153","title":"Unifying Vision-Language Representation Space with Single-tower Transformer","created":"2022-11-21","cited_by_count":22,"area":null},{"id":"2306.04670","title":"Object Detection with Transformers: A Review","created":"2023-06-07","cited_by_count":22,"area":null},{"id":"2405.04771","title":"Exploring Vision Transformers for 3D Human Motion-Language Models with Motion Patches","created":"2024-05-08","cited_by_count":22,"area":null},{"id":"2111.05759","title":"Multimodal Transformer with Variable-length Memory for Vision-and-Language Navigation","created":"2021-11-10","cited_by_count":21,"area":null},{"id":"2107.00249","title":"OPT: Omni-Perception Pre-Trainer for Cross-Modal Understanding and Generation","created":"2021-07-01","cited_by_count":20,"area":null},{"id":"2305.14057","title":"Can Language Models Understand Physical Concepts?","created":"2023-05-23","cited_by_count":19,"area":null},{"id":"2104.08066","title":"Effect of Visual Extensions on Natural Language Understanding in Vision-and-Language Models","created":"2021-04-16","cited_by_count":18,"area":null},{"id":"2110.08486","title":"Understanding Multimodal Procedural Knowledge by Sequencing Multimodal Instructional Manuals","created":"2021-10-16","cited_by_count":18,"area":null},{"id":"2201.07366","title":"TriCoLo: Trimodal Contrastive Loss for Text to Shape Retrieval","created":"2022-01-19","cited_by_count":18,"area":null},{"id":"2212.14453","title":"Learning Multimodal Data Augmentation in Feature Space","created":"2022-12-29","cited_by_count":18,"area":null},{"id":"2305.04474","title":"TRIPS: Efficient Vision-and-Language Pre-training with Text-Relevant Image Patch Selection","created":"2023-05-08","cited_by_count":18,"area":null},{"id":"2106.09889","title":"GEM: A General Evaluation Benchmark for Multimodal Tasks","created":"2021-06-18","cited_by_count":16,"area":null},{"id":"2305.11768","title":"Generating Visual Spatial Description via Holistic 3D Scene Understanding","created":"2023-05-19","cited_by_count":16,"area":null},{"id":"2102.03942","title":"Iconographic Image Captioning for Artworks","created":"2021-02-07","cited_by_count":15,"area":null},{"id":"2104.08405","title":"LAMPRET: Layout-Aware Multimodal PreTraining for Document Understanding","created":"2021-04-16","cited_by_count":15,"area":null},{"id":"2310.17290","title":"RIO: A Benchmark for Reasoning Intention-Oriented Objects in Open Environments","created":"2023-10-26","cited_by_count":15,"area":null},{"id":"2107.01671","title":"Cognitive Visual Commonsense Reasoning Using Dynamic Working Memory","created":"2021-07-04","cited_by_count":14,"area":null},{"id":"2110.12567","title":"Alignment Attention by Matching Key and Query Distributions","created":"2021-10-25","cited_by_count":14,"area":null},{"id":"2211.00849","title":"Fine-grained Visual-Text Prompt-Driven Self-Training for Open-Vocabulary Object Detection","created":"2022-11-02","cited_by_count":14,"area":null},{"id":"2404.09942","title":"Knowledge-enhanced Visual-Language Pretraining for Computational Pathology","created":"2024-04-15","cited_by_count":14,"area":null},{"id":"2104.09379","title":"BM-NAS: Bilevel Multimodal Neural Architecture Search","created":"2021-04-19","cited_by_count":13,"area":null},{"id":"2105.05964","title":"Connecting What to Say With Where to Look by Modeling Human Attention Traces","created":"2021-05-12","cited_by_count":13,"area":null},{"id":"2201.05299","title":"A Thousand Words Are Worth More Than a Picture: Natural Language-Centric Outside-Knowledge Visual Question Answering","created":"2022-01-14","cited_by_count":13,"area":null},{"id":"2205.12617","title":"DisinfoMeme: A Multimodal Dataset for Detecting Meme Intentionally Spreading Out Disinformation","created":"2022-05-25","cited_by_count":13,"area":null},{"id":"2108.02924","title":"Interpretable Visual Understanding with Cognitive Attention Network","created":"2021-08-06","cited_by_count":12,"area":null},{"id":"2109.01934","title":"Weakly Supervised Relative Spatial Reasoning for Visual Question Answering","created":"2021-09-04","cited_by_count":12,"area":null},{"id":"2207.13325","title":"SiRi: A Simple Selective Retraining Mechanism for Transformer-based Visual Grounding","created":"2022-07-27","cited_by_count":12,"area":null},{"id":"2103.15974","title":"Domain-robust VQA with diverse datasets and methods but no target labels","created":"2021-03-29","cited_by_count":11,"area":null},{"id":"2303.13455","title":"CoBIT: A Contrastive Bi-directional Image-Text Generation Model","created":"2023-03-23","cited_by_count":11,"area":null},{"id":"2305.17903","title":"Deeply Coupled Cross-Modal Prompt Learning","created":"2023-05-29","cited_by_count":11,"area":null},{"id":"2311.00136","title":"Neuroformer: Multimodal and Multitask Generative Pretraining for Brain Data","created":"2023-10-31","cited_by_count":11,"area":null},{"id":"2404.04452","title":"Vision transformers in domain adaptation and domain generalization: a study of robustness","created":"2024-04-05","cited_by_count":11,"area":null},{"id":"2108.11119","title":"Product-oriented Machine Translation with Cross-modal Cross-lingual Pre-training","created":"2021-08-25","cited_by_count":10,"area":null},{"id":"2305.00581","title":"Multimodal Graph Transformer for Multimodal Question Answering","created":"2023-04-30","cited_by_count":10,"area":null},{"id":"2307.16204","title":"Open-Set Domain Adaptation with Visual-Language Foundation Models","created":"2023-07-30","cited_by_count":10,"area":null},{"id":"2203.05465","title":"LoopITR: Combining Dual and Cross Encoder Architectures for Image-Text Retrieval","created":"2022-03-10","cited_by_count":9,"area":null},{"id":"2305.06407","title":"Combo of Thinking and Observing for Outside-Knowledge VQA","created":"2023-05-10","cited_by_count":9,"area":null},{"id":"2105.11541","title":"Learning Better Visual Dialog Agents with Pretrained Visual-Linguistic Representation","created":"2021-05-24","cited_by_count":8,"area":null},{"id":"2105.14445","title":"Modeling Text-visual Mutual Dependency for Multi-modal Dialog Generation","created":"2021-05-30","cited_by_count":8,"area":null},{"id":"2106.07853","title":"G2DA: Geometry-Guided Dual-Alignment Learning for RGB-Infrared Person Re-Identification","created":"2021-06-15","cited_by_count":8,"area":null}],"next_cursor":"100"}