相关论文: Disentangling Static and Dynamic Information for R…

Research in action detection has grown in the recentyears, as it plays a key role in video understanding. Modelling the interactions (either spatial or temporal) between actors and their context has proven to be essential for this task.…

Detecting changes in data streams is a vital task in many applications. There is increasing interest in changepoint detection in the online setting, to enable real-time monitoring and support prompt responses and informed decision-making.…

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…

One of the most relevant tasks in an intelligent vehicle navigation system is the detection of obstacles. It is important that a visual perception system for navigation purposes identifies obstacles, and it is also important that this…

Machine learning methods adapt the parameters of a model, constrained to lie in a given model class, by using a fixed learning procedure based on data or active observations. Adaptation is done on a per-task basis, and retraining is needed…

This work proposes a learning-based statistical refinement method for improving the denoising results of a given denoiser without knowing the precise noise distribution or accessing clean images or calibration data. While there are many…

Scene Text Recognition (STR) models have achieved high performance in recent years on benchmark datasets where text images are presented with minimal noise. Traditional STR recognition pipelines take a cropped image as sole input and…

Temporal action segmentation approaches have been very successful recently. However, annotating videos with frame-wise labels to train such models is very expensive and time consuming. While weakly supervised methods trained using only…

Computer vision models learn to perform a task by capturing relevant statistics from training data. It has been shown that models learn spurious age, gender, and race correlations when trained for seemingly unrelated tasks like activity…

Radar-based human activity recognition has gained attention as a privacy-preserving alternative to vision and wearable sensors, especially in sensitive environments like long-term care facilities. Micro-Doppler spectrograms derived from…

Temporally consistent dense video annotations are scarce and hard to collect. In contrast, image segmentation datasets (and pre-trained models) are ubiquitous, and easier to label for any novel task. In this paper, we introduce a method to…

To use robots in more unstructured environments, we have to accommodate for more complexities. Robotic systems need more awareness of the environment to adapt to uncertainty and variability. Although cameras have been predominantly used in…

Action segmentation is the task of predicting an action label for each frame of an untrimmed video. As obtaining annotations to train an approach for action segmentation in a fully supervised way is expensive, various approaches have been…

This paper presents a novel approach of representing dynamic visual scenes with static maps generated from video/image streams. Such representation allows easy visual assessment of motion in dynamic environments. These maps are 2D matrices…

Mitigating bias in machine learning models is a critical endeavor for ensuring fairness and equity. In this paper, we propose a novel approach to address bias by leveraging pixel image attributions to identify and regularize regions of…

Correlations between factors of variation are prevalent in real-world data. Exploiting such correlations may increase predictive performance on noisy data; however, often correlations are not robust (e.g., they may change between domains,…

Deep neural networks have demonstrated their ability to automatically extract meaningful features from data. However, in supervised learning, information specific to the dataset used for training, but irrelevant to the task at hand, may…

Real-time human activity recognition plays an essential role in real-world human-centered robotics applications, such as assisted living and human-robot collaboration. Although previous methods based on skeletal data to encode human poses…

Image diffusion models are trained on independently sampled static images. While this is the bedrock task protocol in generative modeling, capturing the temporal world through the lens of static snapshots is information-deficient by design.…

How can unlabeled video augment visual learning? Existing methods perform "slow" feature analysis, encouraging the representations of temporally close frames to exhibit only small differences. While this standard approach captures the fact…