Related papers: Learning Disentangled Identifiers for Action-Custo…
Recently, Transformers have gained significant popularity in image restoration tasks such as image super-resolution and denoising, owing to their superior performance. However, balancing performance and computational burden remains a…
Video recognition models often learn scene-biased action representation due to the spurious correlation between actions and scenes in the training data. Such models show poor performance when the test data consists of videos with unseen…
Disentangled Representation Learning aims to improve the explainability of deep learning methods by training a data encoder that identifies semantically meaningful latent variables in the data generation process. Nevertheless, there is no…
Current techniques for detecting AI-generated text are largely confined to manual feature crafting and supervised binary classification paradigms. These methodologies typically lead to performance bottlenecks and unsatisfactory…
A layout to image (L2I) generation model aims to generate a complicated image containing multiple objects (things) against natural background (stuff), conditioned on a given layout. Built upon the recent advances in generative adversarial…
We introduce a conditional generative model for learning to disentangle the hidden factors of variation within a set of labeled observations, and separate them into complementary codes. One code summarizes the specified factors of variation…
Face images are subject to many different factors of variation, especially in unconstrained in-the-wild scenarios. For most tasks involving such images, e.g. expression recognition from video streams, having enough labeled data is…
Latent Action Models (LAMs) enable the learning of world models from unlabeled video by inferring abstract actions between consecutive frames. However, LAMs face a fundamental trade-off between action abstraction and generation fidelity.…
Action classification in still images has been a popular research topic in computer vision. Labelling large scale datasets for action classification requires tremendous manual work, which is hard to scale up. Besides, the action categories…
Large-scale text-to-image (T2I) diffusion models have showcased incredible capabilities in generating coherent images based on textual descriptions, enabling vast applications in content generation. While recent advancements have introduced…
Detecting facial action units (AU) is one of the fundamental steps in automatic recognition of facial expression of emotions and cognitive states. Though there have been a variety of approaches proposed for this task, most of these models…
To improve the generalization of detectors, for domain adaptive object detection (DAOD), recent advances mainly explore aligning feature-level distributions between the source and single-target domain, which may neglect the impact of…
In order to handle the challenges of autonomous driving, deep learning has proven to be crucial in tackling increasingly complex tasks, such as 3D detection or instance segmentation. State-of-the-art approaches for image-based detection…
Deep learning models trained on audio-visual data have been successfully used to achieve state-of-the-art performance for emotion recognition. In particular, models trained with multitask learning have shown additional performance…
Recent advances in generative models trained on large-scale datasets have made it possible to synthesize high-quality samples across various domains. Moreover, the emergence of strong inversion networks enables not only a reconstruction of…
Recently, many text-to-image diffusion models have excelled at generating high-resolution images from text but struggle with precise control over spatial composition and object counting. To address these challenges, prior works have…
The process of generating data such as images is controlled by independent and unknown factors of variation. The retrieval of these variables has been studied extensively in the disentanglement, causal representation learning, and…
Generating instructional images of human daily actions from an egocentric viewpoint serves as a key step towards efficient skill transfer. In this paper, we introduce a novel problem -- egocentric action frame generation. The goal is to…
We propose a new paradigm to automatically generate training data with accurate labels at scale using the text-to-image synthesis frameworks (e.g., DALL-E, Stable Diffusion, etc.). The proposed approach1 decouples training data generation…
AI-based face recognition, i.e., the re-identification of individuals within images, is an already well established technology for video surveillance, for user authentication, for tagging photos of friends, etc. This paper demonstrates that…