Sequential recommender systems have achieved state-of-the-art recommenda...
The recently proposed segment anything model (SAM) has made a significan...
Chain-of-Thought and Program-Aided Language Models represent two distinc...
We endow Large Language Models (LLMs) with fine-grained self-evaluation ...
Feature matching is a crucial technique in computer vision. Essentially,...
Deep learning (DL) has been a revolutionary technique in various domains...
Recent researches indicate that utilizing the frequency information of i...
Background subtraction (BGS) aims to extract all moving objects in the v...
The gap between the randomly initialized item ID embedding and the
well-...
We see widespread adoption of slate recommender systems, where an ordere...
The imbalance problem is widespread in the field of machine learning, wh...
Machine learning has been widely used in healthcare applications to
appr...
Previous unsupervised domain adaptation methods did not handle the
cross...
There exist challenging problems in 3D human pose estimation mission, su...
Embedding MLP has become a paradigm for modern large-scale recommend...
Untrimmed video understanding such as temporal action detection (TAD) of...
Camera calibration is a crucial technique which significantly influences...
Structural neural network pruning aims to remove the redundant channels ...
In this paper, we present a novel end-to-end network architecture to est...
Semi-supervision is a promising paradigm for Bilingual Lexicon Induction...
Recently unsupervised Bilingual Lexicon Induction (BLI) without any para...
Auto Composing is an active and appealing research area in the past few
...
This technical report presents an overview of our solution used in the
s...
Recently, leveraging on the development of end-to-end convolutional neur...
This paper considers the problem of nonlinear dimensionality reduction.
...
Weakly supervised temporal action localization, which aims at temporally...
Three discriminative representations for face presentation attack detect...
Temporal action proposal generation is an important yet challenging prob...
Recently convolutional neural network (CNN) promotes the development of
...
Robust features are of vital importance to face spoofing detection, beca...
Temporal action detection is a very important yet challenging problem, s...
The region-based Convolutional Neural Network (CNN) detectors such as Fa...
Foreground segmentation in video sequences is a classic topic in compute...
In this notebook paper, we describe our approach in the submission to th...
In this paper, we present an approach to reconstruct 3-D human motion fr...