Exemplar-based sketch-to-photo synthesis allows users to generate
photo-...
The Traveling Salesman Problem (TSP) is a well-known problem in combinat...
Recently, diffusion models like StableDiffusion have achieved impressive...
Online retailers often use third-party demand-side-platforms (DSPs) to
c...
Medical Visual Question Answering (VQA) systems play a supporting role t...
The task of 3D semantic scene graph (3DSSG) prediction in the point clou...
Large AI models, or foundation models, are models recently emerging with...
Semi-supervised semantic segmentation has recently gained increasing res...
Deep learning based image enhancement models have largely improved the
r...
Multi-tiered large memory systems call for rethinking of memory profilin...
In recent years, neural image compression (NIC) algorithms have shown
po...
Weakly supervised temporal action localization (WTAL) aims to localize
a...
Reconstructing a 3D shape based on a single sketch image is challenging ...
The previous deep video compression approaches only use the single scale...
In this paper, a novel second-order method called NG+ is proposed. By
fo...
In this paper, we propose a new deep image compression framework called
...
Learning based video compression attracts increasing attention in the pa...
In this paper, we propose a two-stage deep learning framework called
Vox...
3D object detection in point clouds is a challenging vision task that
be...
Domain adaptation aims to leverage a label-rich domain (the source domai...
Albeit current salient object detection (SOD) works have achieved fantas...
Dilation convolution is a critical mutant of standard convolution neural...
In this work, we introduce a novel task - Humancentric Spatio-Temporal V...
Human walking and gaits involve several complex body parts and are influ...
This paper designs a technique route to generate high-quality panoramic ...
Registration of 3D LiDAR point clouds with optical images is critical in...
A hybrid simulation-based framework involving system dynamics and agent-...
A novel modeling framework is proposed for dynamic scheduling of project...
In the learning based video compression approaches, it is an essential i...
In this paper, we consider large-scale finite-sum nonconvex problems ari...
In this paper, we develop an efficient sketchy empirical natural gradien...
Recently, learning based video compression methods attract increasing
at...
In this work, we propose a new layer-by-layer channel pruning method cal...
Image compression is a widely used technique to reduce the spatial redun...
In order to satisfy safety conditions, a reinforcement learned (RL) agen...
Generative adversarial networks (GANs) have demonstrated great success i...
Deep neural networks (DNN) are growing in capability and applicability. ...
In this paper, a method for malfunctioning smart meter detection, based ...
Spatio-temporal action localization consists of three levels of tasks:
s...
Answer selection (answer ranking) is one of the key steps in many kinds ...
Answer selection is an important subtask of question answering (QA), whe...
Conventional video compression approaches use the predictive coding
arch...
Motivation: Protein secondary structure prediction can provide important...
In this paper, we propose relative projective differential invariants (R...
Skeleton-based human action recognition has attracted a lot of research
...
Geometric moment invariants (GMIs) have been widely used as basic tool i...
In this paper, we propose a new deep network that learns multi-level dee...
Matching pedestrians across multiple camera views known as human
re-iden...
3D action recognition - analysis of human actions based on 3D skeleton d...
Recently, bidirectional recurrent neural network (BRNN) has been widely ...