Related papers: Towards Universal Representation for Unseen Action…

Robustness to domain changes is a key capability for effective deployment of human action recognition systems in real-world scenarios, where action categories at inference can present important domain shifts or even unseen actions from…

Data of different modalities generally convey complimentary but heterogeneous information, and a more discriminative representation is often preferred by combining multiple data modalities like the RGB and infrared features. However in…

Contrastive unsupervised representation learning (CURL) is the state-of-the-art technique to learn representations (as a set of features) from unlabelled data. While CURL has collected several empirical successes recently, theoretical…

Generalized Zero-shot Learning (GZSL) has yielded remarkable performance by designing a series of unbiased visual-semantics mappings, wherein, the precision relies heavily on the completeness of extracted visual features from both seen and…

Recognizing human activities in videos is challenging due to the spatio-temporal complexity and context-dependence of human interactions. Prior studies often rely on single input modalities, such as RGB or skeletal data, limiting their…

Multimodal learning assumes all modality combinations of interest are available during training to learn cross-modal correspondences. In this paper, we challenge this modality-complete assumption for multimodal learning and instead strive…

The core challenge in unsupervised anomaly detection is identifying abnormal patterns without prior knowledge of their characteristics. While existing methods have addressed aspects of this problem, they often struggle to learn a robust…

In this paper, we look at the problem of few-shot classification that aims to learn a classifier for previously unseen classes and domains from few labeled samples. Recent methods use adaptation networks for aligning their features to new…

Since Facial Action Unit (AU) annotations require domain expertise, common AU datasets only contain a limited number of subjects. As a result, a crucial challenge for AU detection is addressing identity overfitting. We find that AUs and…

Human Action Recognition (HAR) aims to understand human behavior and assign a label to each action. It has a wide range of applications, and therefore has been attracting increasing attention in the field of computer vision. Human actions…

Out-of-distribution (OOD) detection targets to detect and reject test samples with semantic shifts, to prevent models trained on in-distribution (ID) dataset from producing unreliable predictions. Existing works only extract the appearance…

Addressing the Out-of-Distribution (OoD) segmentation task is a prerequisite for perception systems operating in an open-world environment. Large foundational models are frequently used in downstream tasks, however, their potential for OoD…

We propose a novel convolutional neural network approach to address the fine-grained recognition problem of multi-view dynamic facial action unit detection. We leverage recent gains in large-scale object recognition by formulating the task…

A unified video and action model holds significant promise for robotics, where videos provide rich scene information for action prediction, and actions provide dynamics information for video prediction. However, effectively combining video…

Models for image representation learning are typically designed for either recognition or generation. Various forms of contrastive learning help models learn to convert images to embeddings that are useful for classification, detection, and…

The paper introduces the UniMER dataset, marking the first study on Mathematical Expression Recognition (MER) targeting complex real-world scenarios. The UniMER dataset includes a large-scale training set, UniMER-1M, which offers…

Human activity recognition (HAR) has been playing an increasingly important role in various domains such as healthcare, security monitoring, and metaverse gaming. Though numerous HAR methods based on computer vision have been developed to…

Ultra-wideband (UWB) through-wall radar has a wide range of applications in non-contact human information detection and monitoring. With the integration of machine learning technology, its potential prospects include the physiological…

Universal image restoration aims to recover clean images from arbitrary real-world degradations using a single inference model. Despite significant progress, existing all-in-one restoration networks do not scale to multiple degradations. As…

Multi-modal learning has achieved remarkable success by integrating information from various modalities, achieving superior performance in tasks like recognition and retrieval compared to uni-modal approaches. However, real-world scenarios…