![](https://sigport.org/sites/default/files/styles/list/public/ProbMCL_ICASSP24_Poster-1.png?itok=lFkA0ZSM)
- Read more about PROBMCL: SIMPLE PROBABILISTIC CONTRASTIVE LEARNING FOR MULTI-LABEL VISUAL CLASSIFICATION
- Log in to post comments
Multi-label image classification presents a challenging task in many domains, including computer vision and medical imaging. Recent advancements have introduced graph-based and transformer-based methods to improve performance and capture label dependencies. However, these methods often include complex modules that entail heavy computation and lack interpretability. In this paper, we propose Probabilistic Multi-label Contrastive Learning (ProbMCL), a novel framework to address these challenges in multi-label image classification tasks.
- Categories:
![](https://sigport.org/sites/default/files/styles/home/public/icassp24_logo_0.jpg?itok=OGpw2wC4)
- Read more about Self-Supervised Face Image Restoration with a One-Shot Reference
- Log in to post comments
For image restoration, methods leveraging priors from generative models have been proposed and demonstrated a promising capacity to robustly restore photorealistic and high-quality results. However, these methods are susceptible to semantic ambiguity, particularly with images that have obviously correct semantics, such as facial images. In this paper, we propose a semantic-aware latent space exploration method for image restoration (SAIR).
- Categories:
![](https://sigport.org/sites/default/files/styles/list/public/imspoc.png?itok=9OEiZNb5)
- Read more about Spectro-spatial hyperspectral image reconstruction from interferometric acquisitions
- Log in to post comments
In the last decade, novel hyperspectral cameras have been developed with particularly desirable characteristics of compactness and short acquisition time, retaining their potential to obtain spectral/spatial resolution competitive with respect to traditional cameras. However, a computational effort is required to recover an interpretable data cube.
poster.pdf
![application/pdf PDF icon](/modules/file/icons/application-pdf.png)
- Categories:
![](/sites/all/themes/dataport/images/light-567757_1920.jpg)
- Read more about RESIDUAL DENSE SWIN TRANSFORMER FOR CONTINUOUS DEPTH-INDEPENDENT ULTRASOUND IMAGING
- Log in to post comments
Ultrasound imaging is crucial for evaluating organ morphology and function, yet depth adjustment can degrade image quality and field-of-view, presenting a depth-dependent dilemma. Traditional interpolation-based zoom-in techniques often sacrifice detail and introduce artifacts. Motivated by the potential of arbitrary-scale super-resolution to naturally address these inherent challenges, we present the Residual Dense Swin Transformer Network (RDSTN), designed to capture the non-local characteristics and long-range dependencies intrinsic to ultrasound images.
- Categories:
![](https://sigport.org/sites/default/files/styles/list/public/teaser_for_sigport.jpg?itok=yhFInVkS)
- Read more about CROSS-LINGUAL LEARNING IN MULTILINGUAL SCENE TEXT RECOGNITION
- Log in to post comments
In this paper, we investigate cross-lingual learning (CLL) for multilingual scene text recognition (STR). CLL transfers knowledge from one language to another. We aim to find the condition that exploits knowledge from high-resource languages for improving performance in low-resource languages. To do so, we first examine if two general insights about CLL discussed in previous works are applied to multilingual STR: (1) Joint learning with high- and low-resource languages may reduce performance on low-resource languages, and (2) CLL works best between typologically similar languages.
- Categories:
![](https://sigport.org/sites/default/files/styles/list/public/IMG_1685.jpeg?itok=-g8Xnbu4)
- Read more about High-order Tensor Pooling with Attention for Action Recognition
- Log in to post comments
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.
- Categories:
![](https://sigport.org/sites/default/files/styles/home/public/icassp24_logo_0.jpg?itok=OGpw2wC4)
- Read more about UNSUPERVISED REMOTE SENSING HAZE REMOVAL BASED ON SALIENCY-GUIDED TRANSMISSION REFINEMENT
- Log in to post comments
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.
- Categories:
![](https://sigport.org/sites/default/files/styles/list/public/cover-high-res%20-%20Copy.png?itok=TI5bRc3f)
- Read more about BOOSTING ZERO-SHOT HUMAN-OBJECT INTERACTION DETECTION WITH VISION-LANGUAGE TRANSFER
- Log in to post comments
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.
- Categories:
![](https://sigport.org/sites/default/files/styles/list/public/IMG_1687_0.jpeg?itok=6JFWsdQn)
- Read more about Flow Dynamics Correction for Action Recognition
- Log in to post comments
Various research studies indicate that action recognition performance highly depends on the types of motions being extracted and how accurate the human actions are represented. In this paper, we investigate different optical flow, and features extracted from these optical flow that capturing both short-term and long-term motion dynamics. We perform power normalization on the magnitude component of optical flow for flow dynamics correction to boost subtle or dampen sudden motions.
- Categories:
![](https://sigport.org/sites/default/files/styles/list/public/icassp2024_Poster__01.png?itok=N30q2jwa)
- Read more about A COMPREHENSIVE FRAMEWORK FOR OCCLUDED HUMAN POSE ESTIMATION
- Log in to post comments
Occlusion presents a significant challenge in human pose estimation. The challenges posed by occlusion can be attributed to the following factors: 1) Data: The collection and annotation of occluded human pose samples are relatively challenging. 2) Feature: Occlusion can cause feature confusion due to the high similarity between the target person and interfering individuals. 3) Inference: Robust inference becomes challenging due to the loss of complete body structural information.
- Categories: