相关论文: Refining Pre-Trained Motion Models

Despite their irresistible success, deep learning algorithms still heavily rely on annotated data. On the other hand, unsupervised settings pose many challenges, especially about determining the right inductive bias in diverse scenarios.…

Temporal action segmentation approaches have been very successful recently. However, annotating videos with frame-wise labels to train such models is very expensive and time consuming. While weakly supervised methods trained using only…

Medical imaging has witnessed remarkable progress but usually requires a large amount of high-quality annotated data which is time-consuming and costly to obtain. To alleviate this burden, semi-supervised learning has garnered attention as…

Pre-trained vision-language models learn massive data to model unified representations of images and natural languages, which can be widely applied to downstream machine learning tasks. In addition to zero-shot inference, in order to better…

We propose a deep video prediction model conditioned on a single image and an action class. To generate future frames, we first detect keypoints of a moving object and predict future motion as a sequence of keypoints. The input image is…

We propose a self-supervised method for learning motion-focused video representations. Existing approaches minimize distances between temporally augmented videos, which maintain high spatial similarity. We instead propose to learn…

Self-training is an important technique for solving semi-supervised learning problems. It leverages unlabeled data by generating pseudo-labels and combining them with a limited labeled dataset for training. The effectiveness of…

We address the problem of extracting key steps from unlabeled procedural videos, motivated by the potential of Augmented Reality (AR) headsets to revolutionize job training and performance. We decompose the problem into two steps:…

Semi-supervised learning (SSL) addresses the lack of labeled data by exploiting large unlabeled data through pseudolabeling. However, in the extremely low-label regime, pseudo labels could be incorrect, a.k.a. the confirmation bias, and the…

Performing low hertz labeling for surgical videos at intervals can greatly releases the burden of surgeons. In this paper, we study the semi-supervised instrument segmentation from robotic surgical videos with sparse annotations. Unlike…

In many applications, training machine learning models involves using large amounts of human-annotated data. Obtaining precise labels for the data is expensive. Instead, training with weak supervision provides a low-cost alternative. We…

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.,…

Dense Bird's Eye View (BEV) semantic maps are central to autonomous driving, yet current multi-camera methods depend on costly, inconsistently annotated BEV ground truth. We address this limitation with a two-phase training strategy for…

Learning robust contextual knowledge from unlabeled videos is essential for advancing self-supervised tracking. However, conventional self-supervised trackers lack effective context modeling, while existing context association methods based…

Supervised machine learning provides state-of-the-art solutions to a wide range of computer vision problems. However, the need for copious labelled training data limits the capabilities of these algorithms in scenarios where such input is…

Recent advances in deep learning have achieved promising performance for medical image analysis, while in most cases ground-truth annotations from human experts are necessary to train the deep model. In practice, such annotations are…

A key challenge in self-supervised video representation learning is how to effectively capture motion information besides context bias. While most existing works implicitly achieve this with video-specific pretext tasks (e.g., predicting…

Self-supervised methods have emerged as a promising avenue for representation learning in the recent years since they alleviate the need for labeled datasets, which are scarce and expensive to acquire. Contrastive methods are a popular…

Recent single image unsupervised representation learning techniques show remarkable success on a variety of tasks. The basic principle in these works is instance discrimination: learning to differentiate between two augmented versions of…

The Audio-Visual Video Parsing task aims to identify and temporally localize the events that occur in either or both the audio and visual streams of audible videos. It often performs in a weakly-supervised manner, where only video event…