Related papers: Trading-off Mutual Information on Feature Aggregat…

Due to the rising concern of data privacy, it's reasonable to assume the local client data can't be transferred to a centralized server, nor their associated identity label is provided. To support continuous learning and fill the last-mile…

Discriminative correlation filters (DCF) with deep convolutional features have achieved favorable performance in recent tracking benchmarks. However, most of existing DCF trackers only consider appearance features of current frame, and…

Real world images often have highly imbalanced content density. Some areas are very uniform, e.g., large patches of blue sky, while other areas are scattered with many small objects. Yet, the commonly used successive grid downsampling…

In video person re-identification (Re-ID), the network must consistently extract features of the target person from successive frames. Existing methods tend to focus only on how to use temporal information, which often leads to networks…

Federated learning (FL) is a promising distributed paradigm, eliminating the need for data sharing but facing challenges from data heterogeneity. Personalized parameter generation through a hypernetwork proves effective, yet existing…

In this paper, we develop an orthogonal-frequency-division-multiplexing (OFDM)-based over-the-air (OTA) aggregation solution for wireless federated learning (FL). In particular, the local gradients in massive IoT devices are modulated by an…

Deriving an effective facial expression recognition component is important for a successful human-computer interaction system. Nonetheless, recognizing facial expression remains a challenging task. This paper describes a novel approach…

Identifying robust and accurate correspondences across images is a fundamental problem in computer vision that enables various downstream tasks. Recent semi-dense matching methods emphasize the effectiveness of fusing relevant cross-view…

Transformer-based methods have demonstrated impressive performance in low-level visual tasks such as Image Super-Resolution (SR). However, its computational complexity grows quadratically with the spatial resolution. A series of works…

More powerful feature representations derived from deep neural networks benefit visual tracking algorithms widely. However, the lack of exploitation on temporal information prevents tracking algorithms from adapting to appearances changing…

Humans recognize anomalies through two aspects: larger patch-wise representation discrepancies and weaker patch-to-normal-patch correlations. However, the previous AD methods didn't sufficiently combine the two complementary aspects to…

We propose a novel framework for image clustering that incorporates joint representation learning and clustering. Our method consists of two heads that share the same backbone network - a "representation learning" head and a "clustering"…

Personalized Federated Learning (PFL) aims to learn personalized models for each client based on the knowledge across all clients in a privacy-preserving manner. Existing PFL methods generally assume that the underlying global data across…

In mobile and IoT systems, Federated Learning (FL) is increasingly important for effectively using data while maintaining user privacy. One key challenge in FL is managing statistical heterogeneity, such as non-i.i.d. data, arising from…

In Heterogeneous Face Recognition (HFR), the objective is to match faces across two different domains such as visible and thermal. Large domain discrepancy makes HFR a difficult problem. Recent methods attempting to fill the gap via…

Although human action anticipation is a task which is inherently multi-modal, state-of-the-art methods on well known action anticipation datasets leverage this data by applying ensemble methods and averaging scores of unimodal anticipation…

Multi-scale features have been proven highly effective for object detection but often come with huge and even prohibitive extra computation costs, especially for the recent Transformer-based detectors. In this paper, we propose Iterative…

Federated learning (FL) is an emerging paradigm that permits a large number of clients with heterogeneous data to coordinate learning of a unified global model without the need to share data amongst each other. A major challenge in…

Blind face restoration is a challenging task due to the unknown and complex degradation. Although face prior-based methods and reference-based methods have recently demonstrated high-quality results, the restored images tend to contain…

Multi-modal medical image fusion is essential for the precise clinical diagnosis and surgical navigation since it can merge the complementary information in multi-modalities into a single image. The quality of the fused image depends on the…