{"list":"other","total":66,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"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":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"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":"2203.11171","title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","created":"2022-03-21","cited_by_count":5708},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"2010.04159","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","created":"2020-10-08","cited_by_count":3422},{"id":"2203.15556","title":"Training Compute-Optimal Large Language Models","created":"2022-03-29","cited_by_count":3019},{"id":"1504.08083","title":"Fast R-CNN","created":"2015-04-30","cited_by_count":2933},{"id":"2304.10592","title":"MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models","created":"2023-04-20","cited_by_count":2711},{"id":"2312.14238","title":"InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks","created":"2023-12-21","cited_by_count":2565},{"id":"2211.05100","title":"BLOOM: A 176B-Parameter Open-Access Multilingual Language Model","created":"2022-11-09","cited_by_count":1984},{"id":"2307.03109","title":"A Survey on Evaluation of Large Language Models","created":"2023-07-06","cited_by_count":1242},{"id":"2306.14824","title":"Kosmos-2: Grounding Multimodal Large Language Models to the World","created":"2023-06-26","cited_by_count":1089},{"id":"2306.13063","title":"Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs","created":"2023-06-22","cited_by_count":974},{"id":"2302.00923","title":"Multimodal Chain-of-Thought Reasoning in Language Models","created":"2023-02-02","cited_by_count":752},{"id":"2210.03493","title":"Automatic Chain of Thought Prompting in Large Language Models","created":"2022-10-07","cited_by_count":688},{"id":"2106.13884","title":"Multimodal Few-Shot Learning with Frozen Language Models","created":"2021-06-25","cited_by_count":661},{"id":"2210.03057","title":"Language Models are Multilingual Chain-of-Thought Reasoners","created":"2022-10-06","cited_by_count":530},{"id":"1905.12681","title":"What Makes Training Multi-Modal Classification Networks Hard?","created":"2019-05-29","cited_by_count":344},{"id":"1712.00377","title":"Don't Just Assume; Look and Answer: Overcoming Priors for Visual Question Answering","created":"2017-12-01","cited_by_count":339},{"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":"2305.15408","title":"Towards Revealing the Mystery behind Chain of Thought: A Theoretical Perspective","created":"2023-05-24","cited_by_count":294},{"id":"2211.12860","title":"DETRs with Collaborative Hybrid Assignments Training","created":"2022-11-22","cited_by_count":274},{"id":"2006.04315","title":"Counterfactual VQA: A Cause-Effect Look at Language Bias","created":"2020-06-08","cited_by_count":266},{"id":"2305.17216","title":"Generating Images with Multimodal Language Models","created":"2023-05-26","cited_by_count":260},{"id":"2312.06742","title":"Honeybee: Locality-enhanced Projector for Multimodal LLM","created":"2023-12-11","cited_by_count":197},{"id":"2003.06576","title":"Counterfactual Samples Synthesizing for Robust Visual Question Answering","created":"2020-03-14","cited_by_count":153},{"id":"2003.02437","title":"Drone-based RGB-Infrared Cross-Modality Vehicle Detection via Uncertainty-Aware Learning","created":"2020-03-05","cited_by_count":152},{"id":"2301.13823","title":"Grounding Language Models to Images for Multimodal Inputs and Outputs","created":"2023-01-31","cited_by_count":131},{"id":"2111.00273","title":"Cross-Modality Fusion Transformer for Multispectral Object Detection","created":"2021-10-30","cited_by_count":86},{"id":"2009.12664","title":"Multispectral Fusion for Object Detection with Cyclic Fuse-and-Refine Blocks","created":"2020-09-26","cited_by_count":85},{"id":"2008.03043","title":"Improving Multispectral Pedestrian Detection by Addressing Modality Imbalance Problems","created":"2020-08-07","cited_by_count":83},{"id":"1611.02644","title":"Multispectral Deep Neural Networks for Pedestrian Detection","created":"2016-11-08","cited_by_count":82},{"id":"2308.07504","title":"ICAFusion: Iterative Cross-Attention Guided Feature Fusion for Multispectral Object Detection","created":"2023-08-15","cited_by_count":76},{"id":"1803.05347","title":"Illumination-aware Faster R-CNN for Robust Multispectral Pedestrian Detection","created":"2018-03-14","cited_by_count":74},{"id":"2104.02904","title":"Multimodal Object Detection via Probabilistic Ensembling","created":"2021-04-07","cited_by_count":68},{"id":"2009.08566","title":"MUTANT: A Training Paradigm for Out-of-Distribution Generalization in Visual Question Answering","created":"2020-09-18","cited_by_count":63},{"id":"2010.06572","title":"Does my multimodal model learn cross-modal interactions? It's harder to tell than you might think!","created":"2020-10-13","cited_by_count":62},{"id":"1802.09972","title":"Fusion of Multispectral Data Through Illumination-aware Deep Neural Networks for Pedestrian Detection","created":"2018-02-27","cited_by_count":57},{"id":"2010.10802","title":"Removing Bias in Multi-modal Classifiers: Regularization by Maximizing Functional Entropies","created":"2020-10-21","cited_by_count":57},{"id":"2212.02291","title":"I2MVFormer: Large Language Model Generated Multi-View Document Supervision for Zero-Shot Image Classification","created":"2022-12-05","cited_by_count":54},{"id":"1808.04818","title":"Multispectral Pedestrian Detection via Simultaneous Detection and Segmentation","created":"2018-08-14","cited_by_count":49},{"id":"1909.08580","title":"Re-ID Driven Localization Refinement for Person Search","created":"2019-09-18","cited_by_count":41},{"id":"2403.09972","title":"Think Twice Before Trusting: Self-Detection for Large Language Models through Comprehensive Answer Reflection","created":"2024-03-15","cited_by_count":41},{"id":"1704.02431","title":"Learning Cross-Modal Deep Representations for Robust Pedestrian Detection","created":"2017-04-08","cited_by_count":34},{"id":"1404.7796","title":"Majority Vote of Diverse Classifiers for Late Fusion","created":"2014-04-30","cited_by_count":23},{"id":"2008.02520","title":"Dual Gaussian-based Variational Subspace Disentanglement for Visible-Infrared Person Re-Identification","created":"2020-08-06","cited_by_count":23},{"id":"2201.02356","title":"Cross-Modality Deep Feature Learning for Brain Tumor Segmentation","created":"2022-01-07","cited_by_count":22},{"id":"2402.05457","title":"It's Never Too Late: Fusing Acoustic Information into Large Language Models for Automatic Speech Recognition","created":"2024-02-08","cited_by_count":22},{"id":"2304.07230","title":"PARFormer: Transformer-based Multi-Task Network for Pedestrian Attribute Recognition","created":"2023-04-14","cited_by_count":19},{"id":"2306.03932","title":"Q: How to Specialize Large Vision-Language Models to Data-Scarce VQA Tasks? A: Self-Train on Unlabeled Images!","created":"2023-06-06","cited_by_count":19},{"id":"2208.00967","title":"Counterfactual Intervention Feature Transfer for Visible-Infrared Person Re-identification","created":"2022-08-01","cited_by_count":18},{"id":"2009.12146","title":"GEFA: Early Fusion Approach in Drug-Target Affinity Prediction","created":"2020-09-25","cited_by_count":16},{"id":"2302.00290","title":"MS-DETR: Multispectral Pedestrian Detection Transformer with Loosely Coupled Fusion and Modality-Balanced Optimization","created":"2023-02-01","cited_by_count":14},{"id":"2403.01300","title":"Causal Mode Multiplexer: A Novel Framework for Unbiased Multispectral Pedestrian Detection","created":"2024-03-02","cited_by_count":13},{"id":"2210.00843","title":"Early or Late Fusion Matters: Efficient RGB-D Fusion in Vision Transformers for 3D Object Recognition","created":"2022-10-03","cited_by_count":12},{"id":"2302.12589","title":"Revisiting Modality Imbalance In Multimodal Pedestrian Detection","created":"2023-02-24","cited_by_count":10},{"id":"2311.01025","title":"Integrating Language-Derived Appearance Elements with Visual Cues in Pedestrian Detection","created":"2023-11-02","cited_by_count":10},{"id":"2204.13004","title":"Defending Person Detection Against Adversarial Patch Attack by using Universal Defensive Frame","created":"2022-04-27","cited_by_count":9}],"next_cursor":null}