Computer vision (CV) pipelines are typically evaluated on datasets proce...
With strong representation capabilities, pretrained vision-language mode...
Image-text retrieval requires the system to bridge the heterogenous gap
...
Deep unrolling networks that utilize sparsity priors have achieved great...
With the rapid development of Internet of Things technologies, the next
...
Unlike most previous HOI methods that focus on learning better human-obj...
Camera-only 3D detection provides an economical solution with a simple
c...
Federated learning (FL) enables multiple clients to train a machine lear...
Prompt learning recently become an effective linguistic tool to motivate...
Emotional Support Conversation (ESConv) aims to reduce help-seekers'emot...
The effectiveness of prompt learning has been demonstrated in different
...
3D point cloud semantic segmentation is one of the fundamental tasks for...
Controllable story generation is a challenging task in the field of NLP,...
Multi-agent collaborative perception could significantly upgrade the
per...
Motivations, emotions, and actions are inter-related essential factors i...
While the methods exploiting the tensor low-rank prior are booming in
hi...
Sequential recommendation (SR) aims to predict the subsequent behaviors ...
Drones equipped with cameras can significantly enhance human ability to
...
Collaborative perception has recently shown great potential to improve
p...
Persuasive strategy recognition task requires the system to recognize th...
Federated Learning (FL) enables training a global model without sharing ...
While low-rank matrix prior has been exploited in dynamic MR image
recon...
Low-rank tensor models have been applied in accelerating dynamic magneti...
In this paper, we propose a new test for checking the parametric form of...
Intention, emotion and action are important psychological factors in hum...
Emotional support conversation aims at reducing the emotional distress o...
Knowledge-based visual question answering requires the ability of associ...
Story Ending Generation (SEG) is a challenging task in natural language
...
Intention, emotion and action are important elements in human activities...
Measuring the built and natural environment at a fine-grained scale is n...
End-to-End intelligent neural dialogue systems suffer from the problems ...
It is prevalent to utilize external knowledge to help machine answer
que...
Question answering systems usually use keyword searches to retrieve pote...
We propose HOI Transformer to tackle human object interaction (HOI) dete...
This paper introduces our systems for all three subtasks of SemEval-2021...
Event detection has been an important task in transportation, whose task...
Modeling user interests is crucial in real-world recommender systems. In...
We propose a novel Bi-directional Cognitive Knowledge Framework (BCKF) f...
As a sequence-to-sequence generation task, neural machine translation (N...
Scene graphs are semantic abstraction of images that encourage visual
un...
Knowledge-based Visual Question Answering (KVQA) requires external knowl...
Recent studies have demonstrated the overwhelming advantage of cross-lin...
Visual Dialogue task requires an agent to be engaged in a conversation w...
This paper introduces our systems for the first two subtasks of SemEval
...
Fact-based Visual Question Answering (FVQA) requires external knowledge
...
Fact-based Visual Question Answering (FVQA) requires external knowledge
...
Recent evidence reveals that Neural Machine Translation (NMT) models wit...
Motion prediction is essential and challenging for autonomous vehicles a...
This paper contributes towards the benchmarking of control architectures...
Different from Visual Question Answering task that requires to answer on...