Related papers: MINI-Net: Multiple Instance Ranking Network for Vi…

Recently, few-shot video classification has received an increasing interest. Current approaches mostly focus on effectively exploiting the temporal dimension in videos to improve learning under low data regimes. However, most works have…

This paper strives for video event detection using a representation learned from deep convolutional neural networks. Different from the leading approaches, who all learn from the 1,000 classes defined in the ImageNet Large Scale Visual…

Various multi-instance learning (MIL) based approaches have been developed and successfully applied to whole-slide pathological images (WSI). Existing MIL methods emphasize the importance of feature aggregators, but largely neglect the…

Weakly supervised instance segmentation with image-level labels, instead of expensive pixel-level masks, remains unexplored. In this paper, we tackle this challenging problem by exploiting class peak responses to enable a classification…

Patch-level image representation is very important for object classification and detection, since it is robust to spatial transformation, scale variation, and cluttered background. Many existing methods usually require fine-grained…

Recently, there is an increasing interest in highlight detection research where the goal is to create a short duration video from a longer video by extracting its interesting moments. However, most existing methods ignore the fact that the…

Recent advancements in weakly-supervised video anomaly detection have achieved remarkable performance by applying the multiple instance learning paradigm based on multimodal foundation models such as CLIP to highlight anomalous instances…

In this paper, we introduce a new problem, named audio-visual video parsing, which aims to parse a video into temporal event segments and label them as either audible, visible, or both. Such a problem is essential for a complete…

Weakly supervised nuclei segmentation is a critical problem for pathological image analysis and greatly benefits the community due to the significant reduction of labeling cost. Adopting point annotations, previous methods mostly rely on…

Weakly-supervised temporal action localization aims to localize action instances temporal boundary and identify the corresponding action category with only video-level labels. Traditional methods mainly focus on foreground and background…

The high cost of pixel-level annotations makes it appealing to train saliency detection models with weak supervision. However, a single weak supervision source usually does not contain enough information to train a well-performing model. To…

In the context of the highly increasing number of features that are available nowadays we design a robust and fast method for feature selection. The method tries to select the most representative features that are independent from each…

Despite the great success of the deep features in content-based image retrieval, the visual instance search remains challenging due to the lack of effective instance-level feature representation. Supervised or weakly supervised object…

We address a weakly-supervised low-shot instance segmentation, an annotation-efficient training method to deal with novel classes effectively. Since it is an under-explored problem, we first investigate the difficulty of the problem and…

Viewpoint estimation for known categories of objects has been improved significantly thanks to deep networks and large datasets, but generalization to unknown categories is still very challenging. With an aim towards improving performance…

A major obstacle in instance segmentation is that existing methods often need many per-pixel labels in order to be effective. These labels require large human effort and for certain applications, such labels are not readily available. To…

The main obstacle to weakly supervised semantic image segmentation is the difficulty of obtaining pixel-level information from coarse image-level annotations. Most methods based on image-level annotations use localization maps obtained from…

Despite the recent advances in video classification, progress in spatio-temporal action recognition has lagged behind. A major contributing factor has been the prohibitive cost of annotating videos frame-by-frame. In this paper, we present…

State-of-the-art audio event detection (AED) systems rely on supervised learning using strongly labeled data. However, this dependence severely limits scalability to large-scale datasets where fine resolution annotations are too expensive…

Perception techniques for autonomous driving should be adaptive to various environments. In the case of traffic line detection, an essential perception module, many condition should be considered, such as number of traffic lines and…