4 citations · 6 across the 9 of their papers we have counts for
9 papers
Control Allocation in Neural Network Optimization: Joint Affine Control of Weight and Bias Updates
Zhang Gongyue, Sheng Yixuan, Wang Zhiyong +3
Optimization algorithms determine not only the magnitude of a neural-network update but also how that update is distributed across parameter channels. We study whether this distrib…
Hidden Boundary Motion in Transformer Optimization: Function-Space Orthogonalization of Affine Weight and Bias Updates
Zhang Gongyue, Sheng Yixuan, Liu donghan +3
Weights and biases are normally optimized as separate parameter tensors, yet they do not represent separate functions when the input to an affine layer has nonzero mean. For an aff…
The Anatomy of Implicit Bias: Information Allocation in Neural Network Training
Zhang Gongyue, Wang Zhiyong, Liu Donghan +3
Implicit bias is usually explained as the preference of an optimization process for certain final solutions and their geometry. This view helps explain where a model finally stops.…
Spectral Scalpel: Amplifying Adjacent Action Discrepancy via Frequency-Selective Filtering for Skeleton-Based Action Segmentation
Haoyu Ji, Bowen Chen, Zhihao Yang +6
Skeleton-based Temporal Action Segmentation (STAS) seeks to densely segment and classify diverse actions within long, untrimmed skeletal motion sequences. However, existing STAS me…
LaDy: Lagrangian-Dynamic Informed Network for Skeleton-based Action Segmentation via Spatial-Temporal Modulation
Haoyu Ji, Xueting Liu, Yu Gao +5
Skeleton-based Temporal Action Segmentation (STAS) aims to densely parse untrimmed skeletal sequences into frame-level action categories. However, existing methods, while proficien…
Text-Derived Relational Graph-Enhanced Network for Skeleton-Based Action Segmentation
Haoyu Ji, Bowen Chen, Weihong Ren +4
Skeleton-based Temporal Action Segmentation (STAS) aims to segment and recognize various actions from long, untrimmed sequences of human skeletal movements. Current STAS methods ty…
Language-Assisted Human Part Motion Learning for Skeleton-Based Temporal Action Segmentation
Bowen Chen, Haoyu Ji, Zhiyong Wang +5
Skeleton-based Temporal Action Segmentation involves the dense action classification of variable-length skeleton sequences. Current approaches primarily apply graph-based networks…
Exploring Self- and Cross-Triplet Correlations for Human-Object Interaction Detection
Weibo Jiang, Weihong Ren, Jiandong Tian +3
Human-Object Interaction (HOI) detection plays a vital role in scene understanding, which aims to predict the HOI triplet in the form of <human, object, action>. Existing methods m…
Joint Counting, Detection and Re-Identification for Multi-Object Tracking
Weihong Ren, Denglu Wu, Hui Cao +3
The recent trend in 2D multiple object tracking (MOT) is jointly solving detection and tracking, where object detection and appearance feature (or motion) are learned simultaneousl…