相关论文: Self-supervised Learning for Semi-supervised Tempo…
Natural Language Generation (NLG) accepts input data in the form of images, videos, or text and generates corresponding natural language text as output. Existing NLG methods mainly adopt a supervised approach and rely heavily on coupled…
Semi-supervised learning through deep generative models and multi-lingual pretraining techniques have orchestrated tremendous success across different areas of NLP. Nonetheless, their development has happened in isolation, while the…
Semi-Supervised Semantic Segmentation (S4) aims to train a segmentation model with limited labeled images and a substantial volume of unlabeled images. To improve the robustness of representations, powerful methods introduce a pixel-wise…
Self-supervised learning is an effective way for label-free model pre-training, especially in the video domain where labeling is expensive. Existing self-supervised works in the video domain use varying experimental setups to demonstrate…
Self-training has been shown to be helpful in addressing data scarcity for many domains, including vision, speech, and language. Specifically, self-training, or pseudo-labeling, labels unsupervised data and adds that to the training pool.…
Self-training is an effective approach to semi-supervised learning. The key idea is to let the learner itself iteratively generate "pseudo-supervision" for unlabeled instances based on its current hypothesis. In combination with consistency…
Self-training is a simple yet effective method for semi-supervised learning, during which pseudo-label selection plays an important role for handling confirmation bias. Despite its popularity, applying self-training to landmark detection…
A key challenge for machine intelligence is to learn new visual concepts without forgetting the previously acquired knowledge. Continual learning is aimed towards addressing this challenge. However, there is a gap between existing…
Video Temporal Grounding (VTG) strives to accurately pinpoint event timestamps in a specific video using linguistic queries, significantly impacting downstream tasks like video browsing and editing. Unlike traditional task-specific models,…
This paper presents a production Semi-Supervised Learning (SSL) pipeline based on the student-teacher framework, which leverages millions of unlabeled examples to improve Natural Language Understanding (NLU) tasks. We investigate two…
Video action segmentation under timestamp supervision has recently received much attention due to lower annotation costs. Most existing methods generate pseudo-labels for all frames in each video to train the segmentation model. However,…
Temporal Action Localization (TAL) aims to predict both action category and temporal boundary of action instances in untrimmed videos, i.e., start and end time. Fully-supervised solutions are usually adopted in most existing works, and…
Semi-supervised semantic segmentation relieves the reliance on large-scale labeled data by leveraging unlabeled data. Recent semi-supervised semantic segmentation approaches mainly resort to pseudo-labeling methods to exploit unlabeled…
Temporal Video Grounding (TVG), the task of locating specific video segments based on language queries, is a core challenge in long-form video understanding. While recent Large Vision-Language Models (LVLMs) have shown early promise in…
Deep learning perception models require a massive amount of labeled training data to achieve good performance. While unlabeled data is easy to acquire, the cost of labeling is prohibitive and could create a tremendous burden on companies or…
Attempt to fully discover the temporal diversity and chronological characteristics for self-supervised video representation learning, this work takes advantage of the temporal dependencies within videos and further proposes a novel…
Supervised learning algorithms based on Convolutional Neural Networks have become the benchmark for medical image segmentation tasks, but their effectiveness heavily relies on a large amount of labeled data. However, annotating medical…
Although fully-supervised oriented object detection has made significant progress in multimodal remote sensing image understanding, it comes at the cost of labor-intensive annotation. Recent studies have explored weakly and semi-supervised…
This thesis explores the central question of how to leverage temporal relations among video elements to advance video understanding. Addressing the limitations of existing methods, the work presents a five-fold contribution: (1) an…
Temporal sentence grounding in videos aims to detect and localize one target video segment, which semantically corresponds to a given sentence. Existing methods mainly tackle this task via matching and aligning semantics between a sentence…