Local stochastic gradient descent (SGD) is a fundamental approach in
ach...
The delayed feedback problem is one of the most pressing challenges in
p...
The ability to learn from context with novel concepts, and deliver
appro...
Person clustering with multi-modal clues, including faces, bodies, and
v...
The conventional single-target Cross-Domain Recommendation (CDR) aims to...
Detecting objects based on language descriptions is a popular task that
...
In human conversations, individuals can indicate relevant regions within...
We propose ADCLR: A ccurate and D ense Contrastive Representation Learni...
Recent text-to-image generative models can generate high-fidelity images...
Human intelligence can retrieve any person according to both visual and
...
Referring Expression Segmentation (RES) is a widely explored multi-modal...
We study the trade-off between expectation and tail risk for regret
dist...
Recent years have witnessed a rapid growth of deep generative models, wi...
Open-vocabulary detection (OVD) is an object detection task aiming at
de...
Human-centric perceptions include a variety of vision tasks, which have
...
Human-centric perceptions (e.g., pose estimation, human parsing, pedestr...
Self-supervised learning holds promise in leveraging large numbers of
un...
In recommendation scenarios, there are two long-standing challenges, i.e...
Wall-clock convergence time and communication rounds are critical perfor...
A major bottleneck of distributed learning under parameter-server (PS)
f...
Single-Photon Avalanche Detector (SPAD) arrays are a rapidly emerging
te...
Synchronous local stochastic gradient descent (local SGD) suffers from s...
Loop closing is a fundamental part of simultaneous localization and mapp...
Graph-based models have achieved great success in person re-identificati...
Platooning and coordination are two implementation strategies that are
f...
As a strategy to reduce travel delay and enhance energy efficiency,
plat...
Feature extraction and matching are the basic parts of many computer vis...
We design new policies that ensure both worst-case optimality for expect...
Generalizing learned representations across significantly different visu...
Scalability is an important consideration for deep graph neural networks...
Data is fundamental to machine learning-based products and services and ...
Wall-clock convergence time and communication load are key performance
m...
Graph representation learning has drawn increasing attention in recent y...
Occluded person re-identification (ReID) aims at matching occluded perso...
The growing ubiquity of drones has raised concerns over the ability of
t...
The pretrain-finetune paradigm is a classical pipeline in visual learnin...
Modern neural interfaces allow access to the activity of up to a million...
We consider a reconfigurable intelligent surface (RIS)-aided massive
mul...
Lattice structures and thin-walled tubes are two types of energy-absorbe...
Video object detection is challenging in the presence of appearance
dete...
Cross-Domain Recommendation (CDR) and Cross-System Recommendation (CSR) ...
Motivated by emerging applications such as live-streaming e-commerce,
pr...
Exploiting the relationships between attributes is a key challenge for
i...
Recent years have witnessed significant progress in person re-identifica...
Camera scene detection is among the most popular computer vision problem...
To address the long-standing data sparsity problem in recommender system...
Correspondence selection between two groups of feature points aims to
co...
User data confidentiality protection is becoming a rising challenge in t...
Cross-Domain Recommendation (CDR) and Cross-System Recommendations (CSR)...
To relieve the computational cost of design evaluations using expensive
...