相关论文: MistExit: Learning to Exit for Early Mistake Detec…

In this paper, we propose a conditional early exiting framework for efficient video recognition. While existing works focus on selecting a subset of salient frames to reduce the computation costs, we propose to use a simple sampling…

Mistake analysis in procedural activities is a critical area of research with applications spanning industrial automation, physical rehabilitation, education and human-robot collaboration. This paper reviews vision-based methods for…

Instructional videos provide a convenient modality to learn new tasks (ex. cooking a recipe, or assembling furniture). A viewer will want to find a corresponding video that reflects both the overall task they are interested in as well as…

Mistake action detection is crucial for developing intelligent archives that detect workers' errors and provide feedback. Existing studies have focused on visually apparent mistakes in free-style activities, resulting in video-only…

Mistake detection in procedural tasks is essential for building intelligent systems that support learning and task execution. Existing approaches primarily analyze how an action is performed, while overlooking what it produces, i.e., the…

Deploying deep learning models in time-critical applications with limited computational resources, for instance in edge computing systems and IoT networks, is a challenging task that often relies on dynamic inference methods such as early…

Identifying procedural errors online from egocentric videos is a critical yet challenging task across various domains, including manufacturing, healthcare, and skill-based training. The nature of such mistakes is inherently open-set, as…

Transferring image-based object detectors to the domain of video remains challenging under resource constraints. Previous efforts utilised optical flow to allow unchanged features to be propagated, however, the overhead is considerable when…

Given the enormous number of instructional videos available online, learning a diverse array of multi-step task models from videos is an appealing goal. We introduce a new pre-trained video model, VideoTaskformer, focused on representing…

Promptly identifying procedural errors from egocentric videos in an online setting is highly challenging and valuable for detecting mistakes as soon as they happen. This capability has a wide range of applications across various fields,…

Procedural activity understanding requires perceiving human actions in terms of a broader task, where multiple keysteps are performed in sequence across a long video to reach a final goal state -- such as the steps of a recipe or a DIY…

In this paper, we propose a methodology for early recognition of human activities from videos taken with a first-person viewpoint. Early recognition, which is also known as activity prediction, is an ability to infer an ongoing activity at…

We address the challenge of unsupervised mistake detection in egocentric video of skilled human activities through the analysis of gaze signals. While traditional methods rely on manually labeled mistakes, our approach does not require…

Deploying deep learning services for time-sensitive and resource-constrained settings such as IoT using edge computing systems is a challenging task that requires dynamic adjustment of inference time. Multi-exit architectures allow deep…

Multi-step prediction models, such as diffusion and rectified flow models, have emerged as state-of-the-art solutions for generation tasks. However, these models exhibit higher latency in sampling new frames compared to single-step methods.…

In contrast to the widely studied problem of recognizing an action given a complete sequence, action anticipation aims to identify the action from only partially available videos. As such, it is therefore key to the success of computer…

Reasoning models have demonstrated exceptional performance in tasks such as mathematics and logical reasoning, primarily due to their ability to engage in step-by-step thinking during the reasoning process. However, this often leads to…

Procedure learning involves identifying the key-steps and determining their logical order to perform a task. Existing approaches commonly use third-person videos for learning the procedure, making the manipulated object small in appearance…

Current approaches for activity recognition often ignore constraints on computational resources: 1) they rely on extensive feature computation to obtain rich descriptors on all frames, and 2) they assume batch-mode access to the entire test…

As a simple technique to accelerate inference of large-scale pre-trained models, early exiting has gained much attention in the NLP community. It allows samples to exit early at internal classifiers without passing through the entire model.…