相关论文: Low Pass Filter for Anti-aliasing in Temporal Acti…

The problem of recovering a signal from its low frequency components occurs often in practical applications due to the lowpass behavior of many physical systems. Here we study in detail conditions under which a signal can be determined from…

Existing temporal action detection (TAD) methods rely on generating an overwhelmingly large number of proposals per video. This leads to complex model designs due to proposal generation and/or per-proposal action instance evaluation and the…

In this paper we combine the Alias method with the concept of systematic sampling, a method commonly used in particle filters for efficient low-variance resampling. The proposed method allows very fast sampling from a discrete distribution:…

The focus of this paper is the estimation of a delay between two signals. Such a problem is common in signal processing and particularly challenging when the delay is non-stationary in nature. Our proposed solution is based on an all-pass…

Optical fiber links are known as the most performing tools to transfer ultrastable frequency reference signals. However, these signals are affected by phase noise up to bandwidths of several kilohertz and a careful data processing strategy…

Temporal Action Detection (TAD), the task of localizing and classifying actions in untrimmed video, remains challenging due to action overlaps and variable action durations. Recent findings suggest that TAD performance is dependent on the…

Noisy label problems are inevitably in existence within medical image segmentation causing severe performance degradation. Previous segmentation methods for noisy label problems only utilize a single image while the potential of leveraging…

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.…

Active learning (AL) is a promising ML paradigm that has the potential to parse through large unlabeled data and help reduce annotation cost in domains where labeling data can be prohibitive. Recently proposed neural network based AL…

Detecting actions in videos have been widely applied in on-device applications. Practical on-device videos are always untrimmed with both action and background. It is desirable for a model to both recognize the class of action and localize…

Test-time optimization remains impractical at scale due to prohibitive inference costs--techniques like iterative refinement and multi-step verification can require $10-100\times$ more compute per query than standard decoding. Latent space…

Most modern approaches in temporal action localization divide this problem into two parts: (i) short-term feature extraction and (ii) long-range temporal boundary localization. Due to the high GPU memory cost caused by processing long…

The purpose of model selection algorithms such as All Subsets, Forward Selection and Backward Elimination is to choose a linear model on the basis of the same set of data to which the model will be applied. Typically we have available a…

Probabilistic amplitude shaping (PAS) is a practical means to achieve a shaping gain in optical fiber communication. However, PAS and shaping in general also affect the signal-dependent generation of nonlinear interference. This provides an…

We consider the problem of reconstructing rank-one matrices from random linear measurements, a task that appears in a variety of problems in signal processing, statistics, and machine learning. In this paper, we focus on the Alternating…

Active Learning (AL) has garnered significant interest across various application domains where labeling training data is costly. AL provides a framework that helps practitioners query informative samples for annotation by oracles…

Federated Active Learning (FAL) has emerged as a promising framework to leverage large quantities of unlabeled data across distributed clients while preserving data privacy. However, real-world deployments remain limited by high annotation…

Temporal action segmentation (TAS) demands dense temporal supervision, yet most of the annotation cost in untrimmed videos is spent identifying and refining action transitions, where segmentation errors concentrate and small temporal shifts…

Weakly labelled audio tagging aims to predict the classes of sound events within an audio clip, where the onset and offset times of the sound events are not provided. Previous works have used the multiple instance learning (MIL) framework,…

Ground-based, all-sky astronomical surveys are imposed with an inevitable day-night cadence that can introduce aliases in period-finding methods. We examined four different methods -- three from the literature and a new one that we…