activity
20182022
most citedZero-Shot Heterogeneous Transfer Learning from Recommender Systems to Cold-Start Search Retrieval

27 citations · 50 across the 13 of their papers we have counts for

collaborators

19 papers

cs.LG2022

Robust Time Series Chain Discovery with Incremental Nearest Neighbors

Li Zhang, Yan Zhu, Yifeng Gao +1

Time series motif discovery has been a fundamental task to identify meaningful repeated patterns in time series. Recently, time series chains were introduced as an expansion of tim…

cs.CV2022

Region-Aware Metric Learning for Open World Semantic Segmentation via Meta-Channel Aggregation

Hexin Dong, Zifan Chen, Mingze Yuan +5

As one of the most challenging and practical segmentation tasks, open-world semantic segmentation requires the model to segment the anomaly regions in the images and incrementally…

cs.CV2022

In Defense of Subspace Tracker: Orthogonal Embedding for Visual Tracking

Yao Sui, Guanghui Wang, Li Zhang

The paper focuses on a classical tracking model, subspace learning, grounded on the fact that the targets in successive frames are considered to reside in a low-dimensional subspac…

cs.LG20215 cited

Failure Prediction in Production Line Based on Federated Learning: An Empirical Study

Ning Ge, Guanghao Li, Li Zhang +1

Data protection across organizations is limiting the application of centralized learning (CL) techniques. Federated learning (FL) enables multiple participants to build a learning…

cs.CV2021

Few-shot Action Recognition with Prototype-centered Attentive Learning

Xiatian Zhu, Antoine Toisoul, Juan-Manuel Perez-Rua +3

Few-shot action recognition aims to recognize action classes with few training samples. Most existing methods adopt a meta-learning approach with episodic training. In each episode…

cs.CV2020

Direct Classification of Emotional Intensity

Jacob Ouyang, Isaac R Galatzer-Levy, Vidya Koesmahargyo +1

In this paper, we present a model that can directly predict emotion intensity score from video inputs, instead of deriving from action units. Using a 3d DNN incorporated with dynam…