In recent years, cross-modal reasoning (CMR), the process of understandi...
In this paper, we for the first time explore helpful multi-modal context...
Recently, the no-box adversarial attack, in which the attacker lacks acc...
Weakly-supervised audio-visual video parsing (WS-AVVP) aims to localize ...
We introduce MQ-Det, an efficient architecture and pre-training strategy...
Personalizing generative models offers a way to guide image generation w...
Object Re-identification (ReID) aims to retrieve the probe object from m...
Visual Grounding (VG) refers to locating a region described by expressio...
We present Unified Contrastive Arbitrary Style Transfer (UCAST), a novel...
With the swift advancement of deep learning, state-of-the-art algorithms...
Image manipulation under the guidance of textual descriptions has recent...
Synthesizing high-fidelity complex images from text is challenging. Base...
There is a growing interest in developing unlearnable examples (UEs) aga...
Although significant progress has been made in few-shot learning, most o...
The artistic style within a painting is the means of expression, which
i...
Despite the impressive results of arbitrary image-guided style transfer
...
Digital art synthesis is receiving increasing attention in the multimedi...
Most existing state-of-the-art video classification methods assume the
t...
In this work, we tackle the challenging problem of arbitrary image style...
Collaborative filtering (CF) is widely used by personalized recommendati...
Grounding temporal video segments described in natural language queries
...
We target at the task of weakly-supervised action localization (WSAL), w...
Semi-supervised object detection (SSOD) has achieved substantial progres...
Recently, cluster contrastive learning has been proven effective for per...
Pedestrian trajectory prediction is an important technique of autonomous...
Graph Neural Networks (GNNs) have achieved great success in processing g...
We target at the task of weakly-supervised video object grounding (WSVOG...
In this paper, we present GRecX, an open-source TensorFlow framework for...
The cold-start recommendation is an urgent problem in contemporary onlin...
Weakly supervised object detection (WSOD) has attracted more and more
at...
Vision transformers have recently received explosive popularity, but the...
Video question answering is a challenging task, which requires agents to...
Recently, the transductive graph-based methods have achieved great succe...
Personalized image aesthetic assessment (PIAA) has recently become a hot...
The goal of image style transfer is to render an image with artistic fea...
Big progress has been achieved in domain adaptation in decades. Existing...
Health management is getting increasing attention all over the world.
Ho...
Weakly supervised object localization remains an open problem due to the...
We introduce tf_geometric, an efficient and friendly library for graph d...
Semi-supervised domain adaptation (SSDA) methods have demonstrated great...
Video style transfer is getting more attention in AI community for its
n...
Generative Adversarial Network(GAN) provides a good generative framework...
Multimodal and multi-domain stylization are two important problems in th...
Transductive Zero-shot learning (ZSL) targets to recognize the unseen
ca...
Person search targets to search the probe person from the unconstrainted...
Arbitrary style transfer is a significant topic with both research value...
Adversarial examples provide an opportunity as well as impose a challeng...
Object detection has achieved remarkable progress in the past decade.
Ho...
Controllable painting generation plays a pivotal role in image stylizati...
Existing generalization theories analyze the generalization performance
...