Sorry, you need to enable JavaScript to visit this website.

We aim at capturing high-order statistics of feature vectors formed by a neural network, and propose end-to-end second- and higher-order pooling to form a tensor descriptor. Tensor descriptors require a robust similarity measure due to low numbers of aggregated vectors and the burstiness phenomenon, when a given feature appears more/less frequently than statistically expected. The Heat Diffusion Process (HDP) on a graph Laplacian is closely related to the Eigenvalue Power Normalization (EPN) of the covariance/auto-correlation matrix, whose inverse forms a loopy graph Laplacian.

Haze causes information loss and quality degradation in remote sensing images. Unsupervised learning-based dehazing methods aim to reduce reliance on paired hazy images and their labels. However, complex mapping relationships often increase the difficulty in network convergence, resulting in color distortion and loss of texture details in remote sensing images. To address these issues, we propose an unsupervised haze removal method based on saliency-guided transmission refinement for remote sensing images.

Visual Word Sense Disambiguation (Visual-WSD), as a subtask of fine-grained image-text retrieval, requires a high level of language-vision understanding to capture and exploit the nuanced relationships between text and visual features. However, the cross-linguistic background only with limited contextual information is considered the most significant challenges for this task.

Adversarial face examples possess two critical properties: Visual Quality and Transferability. However, existing approaches rarely address these properties simultaneously, leading to subpar results. To address this issue, we propose a novel adversarial attack technique known as Adversarial Restoration (AdvRestore), which enhances both visual quality and transferability of adversarial face examples by leveraging a face restoration prior. In our approach, we initially train a Restoration Latent Diffusion Model (RLDM) designed for face restoration.

Previous optical flow based video compression is gradually replaced by unsupervised deformable convolution (DCN) based method. This is mainly due to the fact that the motion vector (MV) estimated by the existing optical flow network

Inverse molecular generation is an essential task for drug discovery, and generative models offer a very promising avenue, especially when diffusion models are used. Despite their great success, existing methods are inherently limited by the lack of a semantic latent space that can not be navigated and perform targeted exploration to generate molecules with desired properties.

Current talking avatars mostly generate co-speech gestures based on audio and text of the utterance, without considering the non-speaking motion of the speaker. Furthermore, previous works on co-speech gesture generation have designed network structures based on individual gesture datasets, which results in limited data volume, compromised generalizability, and restricted speaker movements.

Neural semantic parsing maps natural languages (NL) to equivalent formal semantics which are compositional and deduce the sentence meanings by composing smaller parts. To learn a well-defined semantics, semantic parsers must recognize small parts, which are semantic mappings between NL and semantic tokens. Attentions in recent neural models are usually explained as one-on-one semantic mappings. However, attention weights with end-to-end training are shown only weakly correlated with human-labeled mappings. Despite the usefulness, supervised mappings are expensive.

This paper proposes a structure called SPBNet for enhancing binarized convolutional neural networks (BCNNs) using a low-cost 1-D spatial attention structure. Attention blocks can compensate for the performance drop in BCNNs. However, the hardware overhead of complex attention blocks can be a significant burden in BCNNs. The proposed attention block consists of low-cost 1-D height-wise and width-wise 1-D convolutions, It has the attention bias to adjust the effects of attended features in ×0.5 − ×1.5.

Human-Object Interaction (HOI) detection is a crucial task that involves localizing interactive human-object pairs and identifying the actions being performed. Most existing HOI detectors are supervised in nature and lack the ability of zero-shot discovery of unseen interactions. Recently, transformer-based methods have superseded the traditional CNN detectors by aggregating image-wide context but still suffer from the long-tail distribution problem in HOI. In this work, our primary focus is improving HOI detection in images, particularly in zero-shot scenarios.