Cognitive Visual Commonsense Reasoning Using Dynamic Working Memory
Leibniz University of Hannover（汉诺威莱布尼茨大学）；University of Maryland, Baltimore County（马里兰大学巴尔的摩县分校）；China Europe International Business School（中欧国际工商学院）；Auburn University（奥本大学）；Guangdong Pharmaceutical University（广东药科大学）；University of Southern Queensland（南昆士兰大学）
Xuejiao Tang, Xin Huang, Wenbin Zhang, Travers B. Child, Qiong Hu, Zhen Liu, Ji Zhang
Visual Commonsense Reasoning (VCR) predicts an answer with corresponding rationale, given a question-image input. VCR is a recently introduced visual scene understanding task with a wide range of applications, including visual question answering, automated vehicle systems, and clinical decision support. Previous approaches to solving the VCR task generally rely on pre-training or exploiting memory with long dependency relationship encoded models. However, these approaches suffer from a lack of generalizability and prior knowledge. In this paper we propose a dynamic working memory based cognitive VCR network, which stores accumulated commonsense between sentences to provide prior knowledge for inference. Extensive experiments show that the proposed model yields significant improvements over existing methods on the benchmark VCR dataset. Moreover, the proposed model provides intuitive interpretation into visual commonsense reasoning. A Python implementation of our mechanism is publicly available at https://github.com/tanjatang/DMVCR
Improving Generalization in Visual Reasoning via Self-Ensemble
University of Information Technology（信息技术大学）；Vietnam National University, Ho Chi Minh City（胡志明市越南国家大学）；Ho Chi Minh City Open University（胡志明市开放大学）；LPL Financial（LPL金融公司）
Interpretable Visual Understanding with Cognitive Attention Network
Leibniz University of Hannover（汉诺威莱布尼茨大学）；Carnegie Mellon University（卡内基梅隆大学）；National Institute of Informatics（国立信息学研究所）；Moffitt Cancer Center（莫菲特癌症中心）；Vanderbilt University（范德堡大学）；Harvard Medical School（哈佛医学院）；Freie Universität Berlin（柏林自由大学）
Argus Inspection: Do Multimodal Large Language Models Possess the Eye of Panoptes?
Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；The University of Hong Kong（香港大学）；Shanghai Jiao Tong University（上海交通大学）；The Hong Kong University of Science and Technology（香港科学与技术大学）；Fudan University（复旦大学）；Tsinghua University（清华大学）
School of Computer Science and Technology, Huazhong University of Science and Technology（华中科技大学计算机科学与技术学院）；School of Software Engineering, Huazhong University of Science and Technology（华中科技大学软件学院）
Visual Riddles: a Commonsense and World Knowledge Challenge for Large Vision and Language Models
Ben Gurion University（本古里安大学）；Bar-Ilan University（巴伊兰大学）；The Hebrew University of Jerusalem（耶路撒冷希伯来大学）；Google Research（谷歌研究院）；Tel Aviv University（特拉维夫大学）
MemoryVLA: Perceptual-Cognitive Memory in Vision-Language-Action Models for Robotic Manipulation
Department of Automation, BNRist, Tsinghua University（自动化系、BNRist、清华大学）；Dexmal；MEGVII Technology（MEGVII技术）；Tianjin University（天津大学）；Harbin Institute of Technology（哈尔滨工业大学）；StepFun
Decoding the Enigma: Benchmarking Humans and AIs on the Many Facets of Working Memory
Institute for Infocomm Research (I2R), A*STAR（资讯通信研究院（I2R），新加坡科技研究局）；School of Computer Science and Engineering, Nanyang Technological University（南洋理工大学计算机科学与工程学院）
