Related papers: ClawCraneNet: Leveraging Object-level Relation for…

Traditional video reasoning segmentation methods rely on supervised fine-tuning, which limits generalization to out-of-distribution scenarios and lacks explicit reasoning. To address this, we propose \textbf{VideoSeg-R1}, the first…

Recent Multimodal Large Language Models (MLLMs) are remarkable in vision-language tasks, such as image captioning and question answering, but lack the essential perception ability, i.e., object detection. In this work, we address this…

Text-level discourse parsing aims to unmask how two sentences in the text are related to each other. We propose the task of Visual Discourse Parsing, which requires understanding discourse relations among scenes in a video. Here we use the…

Transfer learning has become the de facto standard in computer vision and natural language processing, especially where labeled data is scarce. Accuracy can be significantly improved by using pre-trained models and subsequent fine-tuning.…

Document-level relation extraction aims to extract relations among multiple entity pairs from a document. Previously proposed graph-based or transformer-based models utilize the entities independently, regardless of global information among…

Instance segmentation methods often require costly per-pixel labels. We propose a method that only requires point-level annotations. During training, the model only has access to a single pixel label per object, yet the task is to output…

We introduce a novel robotic system for improving unseen object instance segmentation in the real world by leveraging long-term robot interaction with objects. Previous approaches either grasp or push an object and then obtain the…

Semantic segmentation is a fundamental task in visual scene understanding. We focus on the supervised setting, where ground-truth semantic annotations are available. Based on knowledge about the high regularity of real-world scenes, we…

Deep Convolution Neural Networks (CNNs) have shown impressive performance in various vision tasks such as image classification, object detection and semantic segmentation. For object detection, particularly in still images, the performance…

Unsupervised representation learning techniques, such as learning word embeddings, have had a significant impact on the field of natural language processing. Similar representation learning techniques have not yet become commonplace in the…

In this paper, we introduce a novel network, called discriminative feature network (DFNet), to address the unsupervised video object segmentation task. To capture the inherent correlation among video frames, we learn discriminative features…

Recent advances in deep learning have brought significant progress in visual grounding tasks such as language-guided video object segmentation. However, collecting large datasets for these tasks is expensive in terms of annotation time,…

Humans excel at multisensory perception and can often recognise object properties from the sound of their interactions. Inspired by this, we propose the novel task of Collision Sound Source Segmentation (CS3), where we aim to segment the…

As the intermediate level task connecting image captioning and object detection, visual relationship detection started to catch researchers' attention because of its descriptive power and clear structure. It detects the objects and captures…

Our world can be succinctly and compactly described as structured scenes of objects and relations. A typical room, for example, contains salient objects such as tables, chairs and books, and these objects typically relate to each other by…

Video semantic segmentation requires to utilize the complex temporal relations between frames of the video sequence. Previous works usually exploit accurate optical flow to leverage the temporal relations, which suffer much from heavy…

Visual relationship detection is an intermediate image understanding task that detects two objects and classifies a predicate that explains the relationship between two objects in an image. The three components are linguistically and…

Nowadays, service robots are appearing more and more in our daily life. For this type of robot, open-ended object category learning and recognition is necessary since no matter how extensive the training data used for batch learning, the…

Neural radiance fields are an emerging 3D scene representation and recently even been extended to learn features for scene understanding by distilling open-vocabulary features from vision-language models. However, current method primarily…

In this paper, we address the semantic segmentation problem with a focus on the context aggregation strategy. Our motivation is that the label of a pixel is the category of the object that the pixel belongs to. We present a simple yet…