Related papers: DiffTAD: Temporal Action Detection with Proposal D…

Camouflaged object detection is a challenging task that aims to identify objects that are highly similar to their background. Due to the powerful noise-to-image denoising capability of denoising diffusion models, in this paper, we propose a…

Temporal action detection (TAD) involves the localization and classification of action instances within untrimmed videos. While standard TAD follows fully supervised learning with closed-set setting on large training data, recent zero-shot…

In various scientific and engineering domains, where data acquisition is costly--such as in medical imaging, environmental monitoring, or remote sensing--strategic sampling from unobserved regions, guided by prior observations, is essential…

Denoising Diffusion models have demonstrated their proficiency for generative sampling. However, generating good samples often requires many iterations. Consequently, techniques such as binary time-distillation (BTD) have been proposed to…

Traditional temporal action detection (TAD) usually handles untrimmed videos with small number of action instances from a single label (e.g., ActivityNet, THUMOS). However, this setting might be unrealistic as different classes of actions…

Adversarial purification with diffusion models seeks to project adversarial examples back toward the data manifold, but balancing semantic preservation and robustness against adaptive attacks remains challenging. Recent work shows that…

Existing action detection algorithms usually generate action proposals through an extensive search over the video at multiple temporal scales, which brings about huge computational overhead and deviates from the human perception procedure.…

In recent years, large-scale pre-trained diffusion models have demonstrated their outstanding capabilities in image and video generation tasks. However, existing models tend to produce visual objects commonly found in the training dataset,…

Recent works have shown the promise of inference-time search over action samples for improving generative robot policies. In particular, optimizing cross-chunk coherence via bidirectional decoding has proven effective in boosting the…

Existing Temporal Action Detection (TAD) methods typically take a pre-processing step in converting an input varying-length video into a fixed-length snippet representation sequence, before temporal boundary estimation and action…

Temporal action detection (TAD) aims to determine the semantic label and the temporal interval of every action instance in an untrimmed video. It is a fundamental and challenging task in video understanding. Previous methods tackle this…

Long-term action anticipation has become an important task for many applications such as autonomous driving and human-robot interaction. Unlike short-term anticipation, predicting more actions into the future imposes a real challenge with…

Existing approaches for spatio-temporal action detection in videos are limited by the spatial extent and temporal duration of the actions. In this paper, we present a modular system for spatio-temporal action detection in untrimmed security…

Drivers' visual attention provides critical cues for anticipating latent hazards and directly shapes decision-making and control maneuvers, where its absence can compromise traffic safety. To emulate drivers' perception patterns and advance…

Time series anomaly detection (TSAD) has been an important area of research for decades, with reconstruction-based methods, mostly based on generative models, gaining popularity and demonstrating success. Diffusion models have recently…

Diffusion models with their powerful expressivity and high sample quality have achieved State-Of-The-Art (SOTA) performance in the generative domain. The pioneering Vision Transformer (ViT) has also demonstrated strong modeling capabilities…

Existing audio-text retrieval (ATR) methods are essentially discriminative models that aim to maximize the conditional likelihood, represented as p(candidates|query). Nevertheless, this methodology fails to consider the intrinsic data…

The gradual nature of a diffusion process that synthesizes samples in small increments constitutes a key ingredient of Denoising Diffusion Probabilistic Models (DDPM), which have presented unprecedented quality in image synthesis and been…

We propose the Fourier Adaptive Lite Diffusion Architecture (FALDA), a novel probabilistic framework for time series forecasting. First, we introduce the Diffusion Model for Residual Regression (DMRR) framework, which unifies…

Learning a generalist embodied agent capable of completing multiple tasks poses challenges, primarily stemming from the scarcity of action-labeled robotic datasets. In contrast, a vast amount of human videos exist, capturing intricate tasks…