Related papers: Spider: A Unified Framework for Context-dependent …
The parallel advances in language modeling and speech representation learning have raised the prospect of learning language directly from speech without textual intermediates. This requires extracting semantic representations directly from…
Compressed Image Super-resolution (CSR) aims to simultaneously super-resolve the compressed images and tackle the challenging hybrid distortions caused by compression. However, existing works on CSR usually focuses on a single compression…
The objective of this paper is self-supervised learning of video object segmentation. We develop a unified framework which simultaneously models cross-frame dense correspondence for locally discriminative feature learning and embeds…
Representation learning is a critical ingredient for natural language processing systems. Recent Transformer language models like BERT learn powerful textual representations, but these models are targeted towards token- and sentence-level…
Video subtitle removal aims to distinguish text overlays from background content while preserving temporal coherence. Existing diffusion-based methods necessitate explicit mask sequences during both training and inference phases, which…
Scene change detection (SCD), a crucial perception task, identifies changes by comparing scenes captured at different times. SCD is challenging due to noisy changes in illumination, seasonal variations, and perspective differences across a…
Controllable image semantic understanding tasks, such as captioning or segmentation, necessitate users to input a prompt (e.g., text or bounding boxes) to predict a unique outcome, presenting challenges such as high-cost prompt input or…
Multi-human parsing is an image segmentation task necessitating both instance-level and fine-grained category-level information. However, prior research has typically processed these two types of information through separate branches and…
Camouflaged Object Detection (COD) demands models to expeditiously and accurately distinguish objects which conceal themselves seamlessly in the environment. Owing to the subtle differences and ambiguous boundaries, COD is not only a…
Recent years have witnessed a great development of Convolutional Neural Networks in semantic segmentation, where all classes of training images are simultaneously available. In practice, new images are usually made available in a…
Depth-aware video panoptic segmentation is a promising approach to camera based scene understanding. However, the current state-of-the-art methods require costly video annotations and use a complex training pipeline compared to their…
Unsupervised domain adaptive segmentation aims to improve the segmentation accuracy of models on target domains without relying on labeled data from those domains. This approach is crucial when labeled target domain data is scarce or…
This paper introduces a novel approach to Generalized Category Discovery (GCD) by leveraging the concept of contextuality to enhance the identification and classification of categories in unlabeled datasets. Drawing inspiration from human…
Referring image segmentation is a challenging task that involves generating pixel-wise segmentation masks based on natural language descriptions. The complexity of this task increases with the intricacy of the sentences provided. Existing…
Powered by large-scale pre-training, vision foundation models exhibit significant potential in open-world image understanding. However, unlike large language models that excel at directly tackling various language tasks, vision foundation…
Topic segmentation is important in understanding scientific documents since it can not only provide better readability but also facilitate downstream tasks such as information retrieval and question answering by creating appropriate…
Scene parsing, or semantic segmentation, consists in labeling each pixel in an image with the category of the object it belongs to. It is a challenging task that involves the simultaneous detection, segmentation and recognition of all the…
In order to operate in human environments, a robot's semantic perception has to overcome open-world challenges such as novel objects and domain gaps. Autonomous deployment to such environments therefore requires robots to update their…
This paper describes a fast and accurate semantic image segmentation approach that encodes not only the discriminative features from deep neural networks, but also the high-order context compatibility among adjacent objects as well as low…
Language identification (LID) recognizes the language of a spoken utterance automatically. According to recent studies, LID models trained with an automatic speech recognition (ASR) task perform better than those trained with a LID task…