Related papers: Advancing Weakly-Supervised Audio-Visual Video Par…

Anomaly action detection and localization play an essential role in security and advanced surveillance systems. However, due to the tremendous amount of surveillance videos, most of the available data for the task is unlabeled or…

Audio-visual representation learning is an important task from the perspective of designing machines with the ability to understand complex events. To this end, we propose a novel multimodal framework that instantiates multiple instance…

Dense anticipation aims to forecast future actions and their durations for long horizons. Existing approaches rely on fully-labelled data, i.e. sequences labelled with all future actions and their durations. We present a (semi-) weakly…

Pseudo-labelling is a popular technique in unsuper-vised domain adaptation for semantic segmentation. However, pseudo labels are noisy and inevitably have confirmation bias due to the discrepancy between source and target domains and…

Temporal action segmentation in videos has drawn much attention recently. Timestamp supervision is a cost-effective way for this task. To obtain more information to optimize the model, the existing method generated pseudo frame-wise labels…

Audio-Visual Source Localization (AVSL) is the task of identifying specific sounding objects in the scene given audio cues. In our work, we focus on semi-supervised AVSL with pseudo-labeling. To address the issues with vanilla hard…

This paper addresses semi-supervised semantic segmentation by exploiting a small set of images with pixel-level annotations (strong supervisions) and a large set of images with only image-level annotations (weak supervisions). Most existing…

Semantic segmentation is an important and popular research area in computer vision that focuses on classifying pixels in an image based on their semantics. However, supervised deep learning requires large amounts of data to train models and…

The task of weakly supervised temporal action localization targets at generating temporal boundaries for actions of interest, meanwhile the action category should also be classified. Pseudo-label-based methods, which serve as an effective…

Semi-supervised object detection methods are widely used in autonomous driving systems, where only a fraction of objects are labeled. To propagate information from the labeled objects to the unlabeled ones, pseudo-labels for unlabeled…

Semi-supervised semantic segmentation methods leverage unlabeled data by pseudo-labeling them. Thus the success of these methods hinges on the reliablility of the pseudo-labels. Existing methods mostly choose high-confidence pixels in an…

Recent advances in semi-supervised learning (SSL) demonstrate that a combination of consistency regularization and pseudo-labeling can effectively improve image classification accuracy in the low-data regime. Compared to classification,…

Frame-by-frame annotation of bounding boxes by clinical experts is often required to train fully supervised object detection models on medical video data. We propose a method for improving object detection in medical videos through weak…

Dense event captioning aims to detect and describe all events of interest contained in a video. Despite the advanced development in this area, existing methods tackle this task by making use of dense temporal annotations, which is…

We propose a method to perform audio event detection under the common constraint that only limited training data are available. In training a deep learning system to perform audio event detection, two practical problems arise. Firstly, most…

Weakly supervised video anomaly detection aims to detect anomalies and identify abnormal categories with only video-level labels. We propose CPL-VAD, a dual-branch framework with cross pseudo labeling. The binary anomaly detection branch…

In this paper we propose a novel learning framework called Supervised and Weakly Supervised Learning where the goal is to learn simultaneously from weakly and strongly labeled data. Strongly labeled data can be simply understood as fully…

Fine-tuning vision-language models (VLMs) like CLIP to downstream tasks is often necessary to optimize their performance. However, a major obstacle is the limited availability of labeled data. We study the use of pseudolabels, i.e.,…

Supervised learning in large discriminative models is a mainstay for modern computer vision. Such an approach necessitates investing in large-scale human-annotated datasets for achieving state-of-the-art results. In turn, the efficacy of…

Building robust and generic object detection frameworks requires scaling to larger label spaces and bigger training datasets. However, it is prohibitively costly to acquire annotations for thousands of categories at a large scale. We…