Related papers: Weakly Supervised Attention Learning for Textual P…
While image segmentation is crucial in various computer vision applications, such as autonomous driving, grasping, and robot navigation, annotating all objects at the pixel-level for training is nearly impossible. Therefore, the study of…
This paper presents an approach for grounding phrases in images which jointly learns multiple text-conditioned embeddings in a single end-to-end model. In order to differentiate text phrases into semantically distinct subspaces, we propose…
Scribble-based weakly supervised semantic segmentation leverages only a few annotated pixels as labels to train a segmentation model, presenting significant potential for reducing the human labor involved in the annotation process. This…
Visual grounding (VG) is the capability to identify the specific regions in an image associated with a particular text description. In medical imaging, VG enhances interpretability by highlighting relevant pathological features…
We introduce the problem of weakly supervised Multi-Object Tracking and Segmentation, i.e. joint weakly supervised instance segmentation and multi-object tracking, in which we do not provide any kind of mask annotation. To address it, we…
Recent advances in self-supervised learning (SSL) have largely closed the gap with supervised ImageNet pretraining. Despite their success these methods have been primarily applied to unlabeled ImageNet images, and show marginal gains when…
The 3D weakly-supervised visual grounding task aims to localize oriented 3D boxes in point clouds based on natural language descriptions without requiring annotations to guide model learning. This setting presents two primary challenges:…
Transformers for visual-language representation learning have been getting a lot of interest and shown tremendous performance on visual question answering (VQA) and grounding. But most systems that show good performance of those tasks still…
Temporal grounding of natural language in untrimmed videos is a fundamental yet challenging multimedia task facilitating cross-media visual content retrieval. We focus on the weakly supervised setting of this task that merely accesses to…
Weakly supervised semantic segmentation is a challenging task as it only takes image-level information as supervision for training but produces pixel-level predictions for testing. To address such a challenging task, most recent…
Weakly-supervised semantic segmentation (WSSS) with image-level labels is an important and challenging task. Due to the high training efficiency, end-to-end solutions for WSSS have received increasing attention from the community. However,…
Language grounding is an active field aiming at enriching textual representations with visual information. Generally, textual and visual elements are embedded in the same representation space, which implicitly assumes a one-to-one…
Weakly supervised semantic segmentation (WSSS) in histopathology seeks to reduce annotation cost by learning from image-level labels, yet it remains limited by inter-class homogeneity, intra-class heterogeneity, and the region-shrinkage…
Given a natural language query, a phrase grounding system aims to localize mentioned objects in an image. In weakly supervised scenario, mapping between image regions (i.e., proposals) and language is not available in the training set.…
Solving text classification in a weakly supervised manner is important for real-world applications where human annotations are scarce. In this paper, we propose to query a masked language model with cloze style prompts to obtain supervision…
Subject-driven text-to-image diffusion models empower users to tailor the model to new concepts absent in the pre-training dataset using a few sample images. However, prevalent subject-driven models primarily rely on single-concept input…
We introduce the task of spatially localizing narrated interactions in videos. Key to our approach is the ability to learn to spatially localize interactions with self-supervision on a large corpus of videos with accompanying transcribed…
We propose a novel model for temporal detection and localization which allows the training of deep neural networks using only counts of event occurrences as training labels. This powerful weakly-supervised framework alleviates the burden of…
Top-down visual attention mechanisms have been used extensively in image captioning and visual question answering (VQA) to enable deeper image understanding through fine-grained analysis and even multiple steps of reasoning. In this work,…
In this paper, we introduce a contextual grounding approach that captures the context in corresponding text entities and image regions to improve the grounding accuracy. Specifically, the proposed architecture accepts pre-trained text token…