Chang Sun,Hui Yuan,Shiqi Jiang et al.
Chang Sun et al.
In recent years, LiDAR point clouds have been widely used in many applications. Since the data volume of LiDAR point clouds is very huge, efficient compression is necessary to reduce their storage and transmission costs. However, existing l...
Generation in Generation: Fluid Co-speech Gesture Synthesis with Generative Continuous Quantization [0.03%]
Jialu Li,Yifan Zhao,Xin Guo et al.
Jialu Li et al.
Motion quantization codebooks have been widely adopted to facilitate co-speech motion generation. However, the conventional quantization-based generation paradigm-which relies on probabilistic token sampling from limited discrete code-books...
Scene Graph-guided SegCaptioning Transformer with Fine-grained Alignment for Controllable Video Segmentation and Captioning [0.03%]
Xu Zhang,Jin Yuan,BinHong Yang et al.
Xu Zhang et al.
Recent advancements in multimodal large models have significantly bridged the representation gap between diverse modalities, catalyzing the evolution of video multimodal interpretation, which enhances users' understanding of video content b...
PePNet: Pose-Enhanced Point Cloud Network for LiDAR-based Human Action Recognition in Outdoor Long-Range Scenarios [0.03%]
Mengyuan Liu,Zhichao Deng,Wanying Zhang et al.
Mengyuan Liu et al.
With potential applications in robotics and autonomous vehicles, LiDAR-based human action recognition (HAR) in outdoor long-range scenarios is challenging due to the degradation of point cloud density with distance and the simultaneous moti...
HistRetinex: Optimizing Retinex Model in Histogram Domain for Efficient Low-Light Image Enhancement [0.03%]
Jingtian Zhao,Xueli Xie,Jianxiang Xi et al.
Jingtian Zhao et al.
Retinex-based low-light image enhancement methods are widely used due to their excellent performance. However, most of them are time-consuming for large-size images. To solve this issue, this paper extends the Retinex model from the spatial...
REMIND: Retrieval-Augmented Reconstruction With Dual Memories for Modality-Missing Object Re-Identification [0.03%]
Zhendong Xu,Zi Wang,Aihua Zheng et al.
Zhendong Xu et al.
To address the modality-missing object Re-Identification (Re-ID) task, a common strategy is to compensate for absent information by exploiting available modalities. However, existing reconstruction-based approaches suffer from two major lim...
Xun Jiang,Xing Xu,Chong Liu et al.
Xun Jiang et al.
To facilitate smart wearable devices or human-like robotics with real-time first-person perspective perception ability, recent researchers proposed the Egocentric Online Action Segmentation (EOAS) task. It requires models to recognize what ...
Yuning Cui,Wenqi Ren,Alois Knoll
Yuning Cui
All-in-one image restoration has recently attracted considerable attention for its ability to address multiple degradation types within a single, unified framework. However, existing methods often incur substantial computational overhead, e...
HAIMNet: A Hierarchical Adaptive Interaction Modulation Network for Low-Light Image Enhancement [0.03%]
Xiaofeng Wang,Ziqian Wang,Meijia Guo et al.
Xiaofeng Wang et al.
Low-light image enhancement (LLIE) is essential for enabling reliable nighttime visual perception and improving the performance of downstream vision tasks, including object detection and image segmentation. Under complex illumination condit...
Boosting Semi-Supervised Learning with Entropy-Guided Adaptive Reward Maximization [0.03%]
基于熵引导自适应奖励最大化的半监督学习促进算法
Anyang Tong,Zenglin Shi,Zhun Zhong et al.
Anyang Tong et al.
Existing semi-supervised learning (SSL) methods rely predominantly on pseudo-labeling and consistency regularization to leverage unlabeled data, demonstrating significant performance improvements. However, we pinpoint that these methods suf...