Related papers: Tag, Copy or Predict: A Unified Weakly-Supervised …

Deep neural networks, albeit their great success on feature learning in various computer vision tasks, are usually considered as impractical for online visual tracking because they require very long training time and a large number of…

The immense success of deep learning based methods in computer vision heavily relies on large scale training datasets. These richly annotated datasets help the network learn discriminative visual features. Collecting and annotating such…

Large Vision-Language Models (VLMs) have been extended to understand both images and videos. Visual token compression is leveraged to reduce the considerable token length of visual inputs. To meet the needs of different tasks, existing…

Recently, significant improvement has been made on semantic object segmentation due to the development of deep convolutional neural networks (DCNNs). Training such a DCNN usually relies on a large number of images with pixel-level…

Weakly-supervised learning based on, e.g., partially labelled images or image-tags, is currently attracting significant attention in CNN segmentation as it can mitigate the need for full and laborious pixel/voxel annotations. Enforcing…

We consider the problem of learning efficient and inductive graph convolutional networks for text classification with a large number of examples and features. Existing state-of-the-art graph embedding based methods such as predictive text…

One key challenge to learning-based video compression is that motion predictive coding, a very effective tool for video compression, can hardly be trained into a neural network. In this paper we propose the concept of PixelMotionCNN (PMCNN)…

Deep convolutional neural networks (CNNs) have been immensely successful in many high-level computer vision tasks given large labeled datasets. However, for video semantic object segmentation, a domain where labels are scarce, effectively…

In the 21st-century information age, with the development of big data technology, effectively extracting valuable information from massive data has become a key issue. Traditional data mining methods are inadequate when faced with…

Monocular 3D object detection typically relies on pseudo-labeling techniques to reduce dependency on real-world annotations. Recent advances demonstrate that deterministic linguistic cues can serve as effective auxiliary weak supervision…

In this paper, we present a simple, flexible and effective vision-language (VL) tracking pipeline, termed \textbf{MMTrack}, which casts VL tracking as a token generation task. Traditional paradigms address VL tracking task indirectly with…

Recent years have witnessed the prevailing progress of Generative Adversarial Networks (GANs) in image-to-image translation. However, the success of these GAN models hinges on ponderous computational costs and labor-expensive training data.…

This paper proposes a new unsupervised domain adaptation approach called Collaborative and Adversarial Network (CAN), which uses the domain-collaborative and domain-adversarial learning strategy for training the neural network. The…

Training a Fully Convolutional Network (FCN) for semantic segmentation requires a large number of masks with pixel level labelling, which involves a large amount of human labour and time for annotation. In contrast, web images and their…

Bioacoustics data from Passive acoustic monitoring (PAM) poses a unique set of challenges for classification, particularly the limited availability of complete and reliable labels in datasets due to annotation uncertainty, biological…

DeepSeek-OCR leverages visual-text compression to reduce long-text processing costs and accelerate inference, yet visual tokens remain prone to redundant textual and structural information. Moreover, current token pruning methods for…

Weakly-supervised learning approaches have gained significant attention due to their ability to reduce the effort required for human annotations in training neural networks. This paper investigates a framework for weakly-supervised object…

Few-shot sequence labeling aims to identify novel classes based on only a few labeled samples. Existing methods solve the data scarcity problem mainly by designing token-level or span-level labeling models based on metric learning. However,…

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…

We present a novel unsupervised feature representation learning method, Visual Commonsense Region-based Convolutional Neural Network (VC R-CNN), to serve as an improved visual region encoder for high-level tasks such as captioning and VQA.…