As critical visual details become obscured, the low visibility and high ISO noise in extremely low-light images pose a significant challenge to human pose estimation. Current methods fail to provide high-quality representations due to reliance on pixel-level enhancements that compromise semantics and the inability to effectively handle extreme low-light conditions for robust feature learning. In this work, we propose a frequency-based framework for low-light human pose estimation, rooted in the "divide-and-conquer" principle. Instead of uniformly enhancing the entire image, our method focuses on task-relevant information. By applying dynamic illumination correction to the low-frequency components and low-rank denoising to the high-frequency components, we effectively enhance both the semantic and texture information essential for accurate pose estimation. As a result, this targeted enhancement method results in robust, high-quality representations, significantly improving pose estimation performance. Extensive experiments demonstrating its superiority over state-of-the-art methods in various challenging low-light scenarios.

Pose distillation is widely adopted to reduce model size in human pose estimation. However, existing methods primarily emphasize the transfer of teacher knowledge while often neglecting the performance degradation resulted from the curse of capacity gap between teacher and student. To address this issue, we propose AgentPose, a novel pose distillation method that integrates a feature agent to model the distribution of teacher features and progressively aligns the distribution of student features with that of the teacher feature, effectively overcoming the capacity gap and enhancing the ability of knowledge transfer. Our comprehensive experiments conducted on the COCO dataset substantiate the effectiveness of our method in knowledge transfer, particularly in scenarios with a high capacity gap.

Synthesizing normal-light novel views from low-light multiview images is an important yet challenging task, given the low visibility and high ISO noise present in the input images. Existing low-light enhancement methods often struggle to effectively preprocess such low-light inputs, as they fail to consider correlations among multiple views. Although other state-of-the-art methods have introduced illumination-related components offering alternative solutions to the problem, they often result in drawbacks such as color distortions and artifacts, and they provide limited denoising effectiveness. In this paper, we propose a novel Robust Low-light Scene Restoration framework (RoSe), which enables effective synthesis of novel views in normal lighting conditions from low-light multiview image inputs, by formulating the task as an illuminance transition estimation problem in 3D space, conceptualizing it as a specialized rendering task. This multiview-consistent illuminance transition field establishes a robust connection between low-light and normal-light conditions. By further exploiting the inherent low-rank property of illumination to constrain the transition representation, we achieve more effective denoising without complex 2D techniques or explicit noise modeling. To implement RoSe, we design a concise dual-branch architecture and introduce a low-rank denoising module. Experiments demonstrate that RoSe significantly outperforms state-of-the-art models in both rendering quality and multiview consistency on standard benchmarks. The codes and data are available at https://pegasus2004.github.io/RoSe.

Accurate and reliable prediction of Alzheimer’s disease (AD) progression is crucial for effective interventions and treatment to delay its onset. Recently, deep learning models for AD progression achieve excellent predictive accuracy. However, their predictions lack reliability due to the non-calibration defects, that affects their recognition and acceptance. To address this issue, this paper proposes a temporal attention-aware evidential recurrent network for trustworthy prediction of AD progression. Specifically, evidential recurrent network explicitly models uncertainty of the output and converts it into a reliability measure for trustworthy AD progression prediction. Furthermore, considering that the actual scenario of AD progression prediction frequently relies on historical longitudinal data, we introduce temporal attention into evidential recurrent network, which improves predictive performance. We demonstrate the proposed model on the TADPOLE dataset. For predictive performance, the proposed model achieves mAUC of 0.943 and BCA of 0.881, which is comparable to the SOTA model MinimalRNN. More importantly, the proposed model provides reliability measures of the predicted results through uncertainty estimation and the ECE of the method on the TADPOLE dataset is 0.101, which is much lower than the SOTA model at 0.147, indicating that the proposed model can provide important decision-making support for risk-sensitive prediction of AD progression.

Trusted open set recognition aims to classify known classes and reject unknown ones, as well as outputs an uncertainty estimate to measure the reliability of recognition results, thus extending the application scenarios of traditional open set recognition methods to risk-sensitive fields. Current methods assume that the covariate distribution of the known classes remains constant during training and testing. However, due to the common occurrence of covariate shift in practical applications, existing methods often suffer from limited generalization. To this end, a causal evidence learning framework, highlighted by the controllable Evidential Uncertainty Guided Adversarial Data Augmentation (EUG-ADA) and Causal Adversarial Disentanglement (CausalAD) strategies, is proposed to support trusted open set recognition under covariate shift. Specifically, EUG-ADA generates high-quality augmentation samples to increase training data diversity, guided by controllable evidential uncertainty and constrained by semantic consistency. Moreover, it is complemented by the CausalAD, which learns causal representations through causal intervention, mitigating the risk of misrecognition of unknown classes caused by the model’s reliance on shortcuts for prediction. The combined effect of EUG-ADA and CausalAD enables the model to learn more generalized and robust causal evidence for trusted open set recognition. Finally, extensive experimental results on both real-world and synthetic data validate the effectiveness of the proposed method, demonstrating that it improves not only open set recognition performance under covariate shift but also the reliability of uncertainty estimates. The code is released onhttps://github.com/ScorpioBao/CEL-OSR.

Human pose estimation has achieved significant progress on images with high imaging resolution. However, low-resolution imagery data bring nontrivial challenges which are still under-studied. To fill this gap, we start with investigating existing methods and reveal that the most dominant heatmap-based methods would suffer more severe model performance degradation from low-resolution, and offset learning is an effective strategy. Established on this observation, in this work we propose a novel Confidence-Aware Learning (CAL) method which further addresses two fundamental limitations of existing offset learning methods: inconsistent training and testing, decoupled heatmap and offset learning. Specifically, CAL selectively weighs the learning of heatmap and offset with respect to ground-truth and most confident prediction, whilst capturing the statistical importance of model output in mini-batch learning manner. Extensive experiments conducted on the COCO benchmark show that our method outperforms significantly the state-of-the-art methods for low-resolution human pose estimation.

While being the de facto standard coordinate representation for human pose estimation, heatmap has not been investigated in-depth. This work fills this gap. For the first time, we find that the process of decoding the predicted heatmaps into the final joint coordinates in the original image space is surprisingly significant for the performance. We further probe the design limitations of the standard coordinate decoding method, and propose a more principled distributionaware decoding method. Also, we improve the standard coordinate encoding process (i.e. transforming ground-truth coordinates to heatmaps) by generating unbiased/accurate heatmaps. Taking the two together, we formulate a novel Distribution-Aware coordinate Representation of Keypoints (DARK) method. Serving as a model-agnostic plug-in, DARK brings about significant performance boost to existing human pose estimation models. Extensive experiments show that DARK yields the best results on two common benchmarks, MPII and COCO. Besides, DARK achieves the 2nd place entry in the ICCV 2019 COCO Keypoints Challenge. The code is available online.

Existing human pose estimation approaches often only consider how to improve the model generalisation performance, but putting aside the significant efficiency problem. This leads to the development of heavy models with poor scalability and cost-effectiveness in practical use. In this work, we investigate the under-studied but practically critical pose model efficiency problem. To this end, we present a new Fast Pose Distillation (FPD) model learning strategy. Specifically, the FPD trains a lightweight pose neural network architecture capable of executing rapidly with low computational cost. It is achieved by effectively transferring the pose structure knowledge of a strong teacher network. Extensive evaluations demonstrate the advantages of our FPD method over a broad range of state-of-the-art pose estimation approaches in terms of model cost-effectiveness on two standard benchmark datasets, MPII Human Pose and Leeds Sports Pose.

Object detection is a significant step of intelligent video surveillance. The existing methods achieve the goals by technically designing or learning special features and detection models. Conversely, we propose a method to simulate the mechanism of memory and prediction in our brain. Firstly, a fix-sized window is slid on a static image to generate sequences. Then, a convolutional neural network extracts the sequence features. Finally, a long short-term memory receives these sequence features in proper order to memorize and recognize the sequential patterns. Our contributions are 1) a memory-based classification model in which both of feature learning and sequence learning are integrated subtly, and 2) a memory-based prediction model which is specially designed to predict the potential object locations in the surveillance scene. Compared with the state-of-the-art methods, our method obtains the best performance on three surveillance datasets. Our method may give some new insights on object detection researches.