Scene-graph generation involves creating a structural representation of the relationships between objects in a scene by predicting subject-object-relation triplets from input data. Existing methods show poor performance in detecting triplets outside of a predefined set, primarily due to their reliance on dependent feature learning. To address this issue, we propose DDS -- a decoupled dynamic scene-graph generation network -- that consists of two independent branches that can disentangle extracted features. The key innovation of the current paper is the decoupling of the features representing the relationships from those of the objects, which enables the detection of novel object-relationship combinations. The DDS model is evaluated on three datasets and outperforms previous methods by a significant margin, especially in detecting previously unseen triplets.
Nanyang Technological University（南洋理工大学）；Advanced Digital Sciences Center（先进数字科学中心）；City University of Hong Kong（香港城市大学）
In order to encode the class correlation and class specific information in image representation, we propose a new local feature learning approach named Deep Discriminative and Shareable Feature Learning (DDSFL). DDSFL aims to hierarchically learn feature transformation filter banks to transform raw pixel image patches to features. The learned filter banks are expected to: (1) encode common visual patterns of a flexible number of categories; (2) encode discriminative information; and (3) hierarchically extract patterns at different visual levels. Particularly, in each single layer of DDSFL, sha…
Current video-based scene graph generation (VidSGG) methods have been found to perform poorly on predicting predicates that are less represented due to the inherent biased distribution in the training data. In this paper, we take a closer look at the predicates and identify that most visual relations (e.g. sit_above) involve both actional pattern (sit) and spatial pattern (above), while the distribution bias is much less severe at the pattern level. Based on this insight, we propose a decoupled label learning (DLL) paradigm to address the intractable visual relation prediction from the pattern…
DeGenseGS: Geometrically and Semantically Decoupled Surgical Scene Understanding in 4D Gaussian Splatting
School of Automation, Southeast University（东南大学自动化学院）；School of Internet of Things, Nanjing University of Posts and Telecommunications（南京邮电大学物联网学院）；Department of Biomedical Engineering, National University of Singapore（新加坡国立大学生物医学工程系）
Harbin Institute of Technology at Shenzhen（哈尔滨工业大学（深圳））；Baidu Inc（百度公司）
Typical text spotters follow the two-stage spotting paradigm which detects the boundary for a text instance first and then performs text recognition within the detected regions. Despite the remarkable progress of such spotting paradigm, an important limitation is that the performance of text recognition depends heavily on the precision of text detection, resulting in the potential error propagation from detection to recognition. In this work, we propose the single shot Self-Reliant Scene Text Spotter v2 (SRSTS v2), which circumvents this limitation by decoupling recognition from detection whil…
Microsoft Research Asia（微软亚洲研究院）；Tsinghua University（清华大学）
Layout generation aims to synthesize realistic graphic scenes consisting of elements with different attributes including category, size, position, and between-element relation. It is a crucial task for reducing the burden on heavy-duty graphic design works for formatted scenes, e.g., publications, documents, and user interfaces (UIs). Diverse application scenarios impose a big challenge in unifying various layout generation subtasks, including conditional and unconditional generation. In this paper, we propose a Layout Diffusion Generative Model (LDGM) to achieve such unification with a single…
GeoState: Learning View-Decoupled Geometry States for 3D World Modeling
Tongji University（同济大学）；Hong Kong Polytechnic University（香港理工大学）；Tencent（腾讯）；Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ)（广东省人工智能与数字经济实验室（深圳））
CineScene: Implicit 3D as Effective Scene Representation for Cinematic Video Generation
The University of Hong Kong（香港大学）；Kling Team, Kuaishou Technology（快手技术 Kling 团队）；Tsinghua University（清华大学）；Zhejiang University（浙江大学）；Microsoft Research Project Page（微软研究院项目页面）
Multi-Timescale Motion-Decoupled Spiking Transformer for Audio-Visual Zero-Shot Learning
Harbin Institute of Technology（哈尔滨工业大学）；Harbin Institute of Technology Suzhou Research Institute（哈尔滨工业大学苏州研究院）；Peking University（北京大学）；School of AI for Science（科学人工智能学院）；Peng Cheng Laboratory（鹏城实验室）
South China University of Technology（华南理工大学）；Lenovo Research（联想研究院）
Text recognition has attracted considerable research interests because of its various applications. The cutting-edge text recognition methods are based on attention mechanisms. However, most of attention methods usually suffer from serious alignment problem due to its recurrency alignment operation, where the alignment relies on historical decoding results. To remedy this issue, we propose a decoupled attention network (DAN), which decouples the alignment operation from using historical decoding results. DAN is an effective, flexible and robust end-to-end text recognizer, which consists of thr…
WorldAlign: Decoupled 4D Reward for World-Consistent Video Generation
The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；The Hong Kong University of Science and Technology（香港科技大学）；KlingAI；The University of Hong Kong（香港大学）
Style-Decoupled Adaptive Routing Network for Underwater Image Enhancement
State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University（测绘遥感信息工程国家重点实验室，武汉大学）；Department of Aeronautical and Aviation Engineering, The Hong Kong Polytechnic University（航空工程系，香港理工大学）
CAD-SLAM: Consistency-Aware Dynamic SLAM with Dynamic-Static Decoupled Mapping
Department of Automation, Shanghai Jiao Tong University（自动化系，上海交通大学）；Department of Computer Science, University College London（计算机科学系，伦敦大学学院）；Department of Engineering, University of Cambridge（工程系，剑桥大学）；Department of Automation, Key Laboratory of System Control and Information Processing of Ministry of Education, State Key Laboratory of Avionics Integration and Aviation System-of-Systems Synthesis, Shanghai Key Laboratory of Navigation and Location Based Services, Shanghai Jiao Tong University（自动化系，教育部系统控制与信息处理重点实验室，航空系统集成与航空系统-of-系统综合国家重点实验室，导航与基于位置的服务上海实验室，上海交通大学）
FinSight-Net:A Physics-Aware Decoupled Network with Frequency-Domain Compensation for Underwater Fish Detection in Smart Aquaculture
Dalian Key Laboratory of Smart Fishery（大连智能渔业重点实验室）；College of Information Engineering, Dalian Ocean University（大连海洋大学信息工程学院）；Key Laboratory of Environment Controlled Aquaculture（环境可控养殖重点实验室）；Dalian Polytechnic University School of International Education（大连职业技术学院国际教育学院）
Peking University（北京大学）；Zhejiang Lab（之江实验室）；University of Oxford（牛津大学）；SenseTime Research（商汤科技研究院）
Existing semantic segmentation approaches either aim to improve the object's inner consistency by modeling the global context, or refine objects detail along their boundaries by multi-scale feature fusion. In this paper, a new paradigm for semantic segmentation is proposed. Our insight is that appealing performance of semantic segmentation requires \textit{explicitly} modeling the object \textit{body} and \textit{edge}, which correspond to the high and low frequency of the image. To do so, we first warp the image feature by learning a flow field to make the object part more consistent. The res…
PrismAD: Decoupled Planning via Semantic Mixture-of-Planners for End-to-End Autonomous Driving
School of Vehicle and Mobility, Tsinghua University（清华大学车辆与运载学院）；State Key Laboratory of Intelligent Green Vehicle and Mobility, Tsinghua University（清华大学智能绿色车辆与出行国家重点实验室）；School of Cyberspace Security, Southeast University（东南大学网络空间安全学院）；School of Computer Science and Engineering, Southeast University（东南大学计算机科学与工程学院）；School of Automotive Engineering, Wuhan University of Technology（武汉理工大学汽车工程学院）；SAIC GM Wuling Automobile Co., Ltd.（上汽通用五菱汽车股份有限公司）
Cross-scene model adaption is crucial for camera relocalization in real scenarios. It is often preferable that a pre-learned model can be fast adapted to a novel scene with as few training samples as possible. The existing state-of-the-art approaches, however, can hardly support such few-shot scene adaption due to the entangling of image feature extraction and scene coordinate regression. To address this issue, we approach camera relocalization with a decoupled solution where feature extraction, coordinate regression, and pose estimation are performed separately. Our key insight is that featur…
PhyScene3D: Physically Consistent Interactive 3D Tabletop Scene Generation
Sun Yat-sen University, China（中山大学）；Peng Cheng Laboratory（鹏城实验室）；Guangdong Key Laboratory of Big Data Analysis and Processing（广东省大数据分析与处理重点实验室）；Huawei（华为）
