Text-to-3D generation from a single-view image is a popular but challeng...
Egocentric action recognition is gaining significant attention in the fi...
A pooling operation is essential for effective graph-level representatio...
Zero-shot transfer learning for Dialogue State Tracking (DST) helps to h...
Multimodal emotion recognition identifies human emotions from various da...
Weakly-Supervised Semantic Segmentation (WSSS) using image-level labels
...
This technical report briefly describes our JDExplore d-team's submissio...
Cross-view multi-object tracking aims to link objects between frames and...
Machine Translation Quality Estimation (QE) is the task of evaluating
tr...
This technical report briefly describes our JDExplore d-team's Vega v2
s...
Self-supervised facial representation has recently attracted increasing
...
We present Twin Answer Sentences Attack (TASA), an adversarial attack me...
We describe the JD Explore Academy's submission of the WMT 2022 shared
g...
Few-shot visual recognition refers to recognize novel visual concepts fr...
Deep neural networks (DNNs) are found to be vulnerable to adversarial no...
Anomaly detection aims at identifying deviant samples from the normal da...
State-of-the-art parametric and non-parametric style transfer approaches...
Graph Neural Networks (GNNs) tend to suffer from high computation costs ...
Node classification is a fundamental graph-based task that aims to predi...
Pluralistic image completion focuses on generating both visually realist...
Scene graph generation (SGG) aims to detect objects and predict their
pa...
Graph neural networks have emerged as a leading architecture for many
gr...
Attention mechanisms have been very popular in deep neural networks, whe...
Recent studies show that Graph Neural Networks (GNNs) are vulnerable to
...
Point cloud segmentation is fundamental in understanding 3D environments...
This paper seeks to provide the information retrieval community with som...
Weakly-supervised semantic segmentation (WSSS) with image-level labels i...
Affective computing is an emerging interdisciplinary field where
computa...
Generating informative scene graphs from images requires integrating and...
Scene Graph Generation (SGG) aims to build a structured representation o...
Over-smoothing is a challenging problem, which degrades the performance ...
The recent success of Transformer has provided a new direction to variou...
Cross-modal retrieval aims to enable flexible retrieval experience by
co...
Unsupervised cross-modal hashing (UCMH) has become a hot topic recently....
In visual relationship detection, human-notated relationships can be reg...