Related papers: Multimodal Visual Concept Learning with Weakly Sup…

Video moment retrieval is to identify the target moment according to the given sentence in an untrimmed video. Due to temporal boundary annotations of the video are extremely time-consuming to acquire, modeling in the weakly-supervised…

Few-shot class-incremental learning(FSCIL) focuses on designing learning algorithms that can continually learn a sequence of new tasks from a few samples without forgetting old ones. The difficulties are that training on a sequence of…

Frame-level micro- and macro-expression spotting methods require time-consuming frame-by-frame observation during annotation. Meanwhile, video-level spotting lacks sufficient information about the location and number of expressions during…

Free-style text is still one of the common ways in which data is registered in real environments, like legal procedures and medical records. Because of that, there have been significant efforts in the area of natural language processing to…

In semi-supervised semantic segmentation, a model is trained with a limited number of labeled images along with a large corpus of unlabeled images to reduce the high annotation effort. While previous methods are able to learn good…

In this work a novel approach for weakly supervised object detection that incorporates pointwise mutual information is presented. A fully convolutional neural network architecture is applied in which the network learns one filter per object…

Unsupervised semantic segmentation requires assigning a label to every pixel without any human annotations. Despite recent advances in self-supervised representation learning for individual images, unsupervised semantic segmentation with…

Language-guided supervision, which utilizes a frozen semantic target from a Pretrained Language Model (PLM), has emerged as a promising paradigm for visual Continual Learning (CL). However, relying on a single target introduces two critical…

Object category localization is a challenging problem in computer vision. Standard supervised training requires bounding box annotations of object instances. This time-consuming annotation process is sidestepped in weakly supervised…

With the surge in available data from various modalities, there is a growing need to bridge the gap between different data types. In this work, we introduce a novel approach to learn cross-modal representations between image data and…

Deep vision models often rely on biases learned from spurious correlations in datasets. To identify these biases, methods that interpret high-level, human-understandable concepts are more effective than those relying primarily on low-level…

We present a deep learning system for testing graphics units by detecting novel visual corruptions in videos. Unlike previous work in which manual tagging was required to collect labeled training data, our weak supervision method is fully…

Weakly supervised semantic segmentation has witnessed great achievements with image-level labels. Several recent approaches use the CLIP model to generate pseudo labels for training an individual segmentation model, while there is no…

Deep supervised models have an unprecedented capacity to absorb large quantities of training data. Hence, training on multiple datasets becomes a method of choice towards strong generalization in usual scenes and graceful performance…

The application of Contrastive Language-Image Pre-training (CLIP) in Weakly Supervised Semantic Segmentation (WSSS) research powerful cross-modal semantic understanding capabilities. Existing methods attempt to optimize input text prompts…

Multiple instance learning (MIL) has emerged as a powerful framework for weakly supervised whole slide image (WSI) classification, enabling slide-level predictions without requiring detailed patch-level annotations. Despite its success, a…

This paper demonstrates a self-supervised approach for learning semantic video representations. Recent vision studies show that a masking strategy for vision and natural language supervision has contributed to developing transferable visual…

Multimodal video summarization requires visual features that align semantically with language generation. Traditional approaches rely on CNN features trained for object classification, which represent visual concepts as discrete categories…

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…

Change detection, which aims to detect spatial changes from a pair of multi-temporal images due to natural or man-made causes, has been widely applied in remote sensing, disaster management, urban management, etc. Most existing change…