相关论文: Cost-Sensitive Learning for Long-Tailed Temporal A…

Real-world data is extremely imbalanced and presents a long-tailed distribution, resulting in models that are biased towards classes with sufficient samples and perform poorly on rare classes. Recent methods propose to rebalance classes but…

Several applications in time series forecasting require predicting multiple steps ahead. Despite the vast amount of literature in the topic, both classical and recent deep learning based approaches have mostly focused on minimising…

The task of temporal grounding aims to locate video moment in an untrimmed video, with a given sentence query. This paper for the first time investigates some superficial biases that are specific to the temporal grounding task, and proposes…

Temporal action localization plays an important role in video analysis, which aims to localize and classify actions in untrimmed videos. The previous methods often predict actions on a feature space of a single-temporal scale. However, the…

The main progress for action segmentation comes from densely-annotated data for fully-supervised learning. Since manual annotation for frame-level actions is time-consuming and challenging, we propose to exploit auxiliary unlabeled videos,…

Current state-of-the-art human activity recognition is focused on the classification of temporally trimmed videos in which only one action occurs per frame. We propose a simple, yet effective, method for the temporal detection of activities…

Imbalanced datasets pose a considerable challenge in training deep learning (DL) models for medical diagnostics, particularly for segmentation tasks. Imbalance may be associated with annotation quality limited annotated datasets, rare…

The standard way of training video models entails sampling at each iteration a single clip from a video and optimizing the clip prediction with respect to the video-level label. We argue that a single clip may not have enough temporal…

Weakly-Supervised Temporal Action Localization (WSTAL) aims to localize actions in untrimmed videos with only video-level labels. Currently, most state-of-the-art WSTAL methods follow a Multi-Instance Learning (MIL) pipeline: producing…

In this paper, we introduce Coarse-Fine Networks, a two-stream architecture which benefits from different abstractions of temporal resolution to learn better video representations for long-term motion. Traditional Video models process…

Video large language models have achieved remarkable performance in tasks such as video question answering, however, their temporal understanding remains suboptimal. To address this limitation, we curate a dedicated instruction fine-tuning…

We propose a simple data model inspired from natural data such as text or images, and use it to study the importance of learning features in order to achieve good generalization. Our data model follows a long-tailed distribution in the…

Temporal action detection (TAD) is an important yet challenging task in video analysis. Most existing works draw inspiration from image object detection and tend to reformulate it as a proposal generation - classification problem. However,…

Long-tailed object detection faces great challenges because of its extremely imbalanced class distribution. Recent methods mainly focus on the classification bias and its loss function design, while ignoring the subtle influence of the…

Localizing actions in video is a core task in computer vision. The weakly supervised temporal localization problem investigates whether this task can be adequately solved with only video-level labels, significantly reducing the amount of…

Long-tailed datasets, where head classes comprise much more training samples than tail classes, cause recognition models to get biased towards the head classes. Weighted loss is one of the most popular ways of mitigating this issue, and a…

The goal of moving object segmentation is separating moving objects from stationary backgrounds in videos. One major challenge in this problem is how to develop a universal model for videos from various natural scenes since previous methods…

With the widespread adoption of deep learning in visual tasks, Class-Incremental Learning (CIL) has become an important paradigm for handling dynamically evolving data distributions. However, CIL faces the core challenge of catastrophic…

Although the performance of Temporal Action Segmentation (TAS) has improved in recent years, achieving promising results often comes with a high computational cost due to dense inputs, complex model structures, and resource-intensive…

Long-tailed class distributions are prevalent among the practical applications of object detection and instance segmentation. Prior work in long-tail instance segmentation addresses the imbalance of losses between rare and frequent…