Related papers: Hierarchical Consistency Learning for Test-time Ad…

Context modeling is essential in learned image compression for accurately estimating the distribution of latents. While recent advanced methods have expanded context modeling capacity, they still struggle to efficiently exploit long-range…

Deep neural network based object detection hasbecome the cornerstone of many real-world applications. Alongwith this success comes concerns about its vulnerability tomalicious attacks. To gain more insight into this issue, we proposea…

Multimodal learning aims to capture both shared and private information from multiple modalities. However, existing methods that project all modalities into a single latent space for fusion often overlook the asynchronous, multi-level…

In this paper, we frame homogeneous-feature multi-task learning (MTL) as a hierarchical representation learning problem, with one task-agnostic and multiple task-specific latent representations. Drawing inspiration from the information…

We introduce a class of concurrent learning (CL) algorithms designed to solve parameter estimation problems with convergence rates ranging from hyperexponential to prescribed-time while utilizing alternating datasets during the learning…

Referring Camouflaged Object Detection (Ref-COD) focuses on segmenting specific camouflaged targets in a query image using category-aligned references. Despite recent advances, existing methods struggle with reference-target semantic…

A fundamental issue for statistical classification models in a streaming environment is that the joint distribution between predictor and response variables changes over time (a phenomenon also known as concept drifts), such that their…

Concealed object segmentation (COS) is a challenging task that involves localizing and segmenting those concealed objects that are visually blended with their surrounding environments. Despite achieving remarkable success, existing COS…

There have been significant advancements in anomaly detection in an unsupervised manner, where only normal images are available for training. Several recent methods aim to detect anomalies based on a memory, comparing or reconstructing the…

In multi-agent reinforcement learning (MARL), the Centralized Training with Decentralized Execution (CTDE) framework is pivotal but struggles due to a gap: global state guidance in training versus reliance on local observations in…

Camouflaged Object Detection (COD) aims to segment targets that share extreme textural and structural similarities with their complex environments. Leveraging their capacity for long-range dependency modeling, Transformer-based detectors…

Human Motion Prediction (HMP) aims to predict future poses at different moments according to past motion sequences. Previous approaches have treated the prediction of various moments equally, resulting in two main limitations: the learning…

Learning semantic-rich representations from raw unlabeled time series data is critical for downstream tasks such as classification and forecasting. Contrastive learning has recently shown its promising representation learning capability in…

Robust cross-subject emotion recognition from multimodal physiological signals remains a challenging problem, primarily due to modality heterogeneity and inter-subject distribution shift. To tackle these challenges, we propose a novel…

State-of-the-art two-stage object detectors apply a classifier to a sparse set of object proposals, relying on region-wise features extracted by RoIPool or RoIAlign as inputs. The region-wise features, in spite of aligning well with the…

Deep learning models fail on cross-domain challenges if the model is oversensitive to domain-specific attributes, e.g., lightning, background, camera angle, etc. To alleviate this problem, data augmentation coupled with consistency…

We introduce TempCLR, a new time-coherent contrastive learning approach for the structured regression task of 3D hand reconstruction. Unlike previous time-contrastive methods for hand pose estimation, our framework considers temporal…

Domain adaptation (DA) aims to transfer knowledge from a label-rich and related domain (source domain) to a label-scare domain (target domain). Pseudo-labeling has recently been widely explored and used in DA. However, this line of research…

Human action recognition (HAR) with multi-modal inputs (RGB-D, skeleton, point cloud) can achieve high accuracy but typically relies on large labeled datasets and degrades sharply when sensors fail or are noisy. We present Robust…

Generalized Category Discovery (GCD) is an emerging and challenging open-world problem that has garnered increasing attention in recent years. Most existing GCD methods focus on discovering categories in static images. However, relying…