Community detection is an important content in complex network analysis....
Video temporal character grouping locates appearing moments of major
cha...
Recognizing target objects using an event-based camera draws more and mo...
This paper aims to tackle a novel task - Temporal Sentence Grounding in
...
Event camera-based pattern recognition is a newly arising research topic...
Performing automatic reformulations of a user's query is a popular parad...
In this work, we introduce a new variant of online gradient descent, whi...
Adversarial training is one of the best-performing methods in improving ...
Real-world graphs generally have only one kind of tendency in their
conn...
Sampled point and voxel methods are usually employed to downsample the d...
General Purpose Graphics Processing Units (GPGPU) are used in most of th...
Learning based feature matching methods have been commonly studied in re...
We introduce Three Towers (3T), a flexible method to improve the contras...
Pretrained language models have achieved remarkable success in various
n...
Existing models for named entity recognition (NER) are mainly based on
l...
Iterative stencils are used widely across the spectrum of High Performan...
Large-scale text-to-image models have demonstrated amazing ability to
sy...
Heterogeneous graph neural networks (HGNNs) as an emerging technique hav...
Existing pedestrian attribute recognition (PAR) algorithms are mainly
de...
Large language models have unlocked strong multi-task capabilities from
...
This paper explores the potential of curriculum learning in LiDAR-based ...
Sampling from high-dimensional distributions is a fundamental problem in...
There has been a recent explosion of computer vision models which perfor...
Existing Transformer-based RGBT tracking methods either use cross-attent...
The last decade has witnessed the proliferation of micro-videos on vario...
Unsupervised learning of vision transformers seeks to pretrain an encode...
With the urgent demand for generalized deep models, many pre-trained big...
In real-world applications, deep learning models often run in non-statio...
Inferential models have been proposed for valid and efficient prior-free...
Estimating the structure of directed acyclic graphs (DAGs) of features
(...
Private multi-winner voting is the task of revealing k-hot binary vector...
Combining the Color and Event cameras (also called Dynamic Vision Sensor...
Exploring sample relationships within each mini-batch has shown great
po...
The main streams of human activity recognition (HAR) algorithms are deve...
While reinforcement learning produces very promising results for many
ap...
Recent studies show that graph convolutional network (GCN) often perform...
Graph Contrastive Learning (GCL), learning the node representations by
a...
Most Graph Neural Networks (GNNs) predict the labels of unseen graphs by...
Effective scaling and a flexible task interface enable large language mo...
Few-shot classification which aims to recognize unseen classes using ver...
Recent trackers adopt the Transformer to combine or replace the widely u...
Text-based person retrieval aims to find the query person based on a tex...
Real-scene image super-resolution aims to restore real-world low-resolut...
Neuromorphic computing is an emerging research field that aims to develo...
Unpaired Image Captioning (UIC) has been developed to learn image
descri...
The idea of robustness is central and critical to modern statistical
ana...
Existing trackers usually select a location or proposal with the maximum...
Ensuring safety of reinforcement learning (RL) algorithms is crucial for...
Ptychography is a popular microscopic imaging modality for many scientif...
We consider non-convex optimization problems with constraint that is a
p...