Hierarchical Variational Autoencoder (HVAE)-based Learned Image Compression (LIC) has shown great promise, but its performance still lags behind autoregressive models due to three key limitations identified: (1) shared latent mappings that lead to accumulated posterior collapse; (2) reliance on static convolutions, limiting adaptability; and (3) gradient imbalance during variable-rate optimization, causing unbalanced performance across different bit rates. To overcome these challenges, we propose QARV++, an improved HVAE-based LIC method. First, we introduce a disentangled latent mapping mechanism, assigning separate transformations to each latent variable to prevent posterior collapse propagation. Second, we integrate deformable convolutions into the network, introducing the DCNNeXt block, which enables dynamic feature adaptation while maintaining computational efficiency. Third, we reformulate variable-rate optimization to ensure balanced gradient updates across different λ values, stabilizing variable-rate training. Extensive experiments demonstrate that QARV++ achieves superior rate-distortion (R-D) performance among HVAE-based LIC models, exhibiting -12.20% -16.34% -15.23% BD-Rate against VVC Intra mode on the Kodak, Tecnick, and CLIC2020 test datasets, respectively. Our approach also generalizes effectively to existing LICs, delivering substantial improvements.
Advances in both lossy image compression and semantic content understanding have been greatly fueled by deep learning techniques, yet these two tasks have been developed separately for the past decades. In this work, we address the problem of directly executing semantic inference from quantized latent features in the deep compressed domain without pixel reconstruction. Although different methods have been proposed for this problem setting, they either are restrictive to a specific architecture, or are sub-optimal in terms of compressed domain task accuracy. In contrast, we propose a lightweight, plug-and-play solution which is generally compliant with popular learned image coders and deep vision models, making it attractive to vast applications. Our method adapts prevalent pixel domain neural models that are deployed for various vision tasks to directly accept quantized latent features (other than pixels). We further suggest training the compressed domain model by transferring knowledge from its corresponding pixel domain counterpart. Experiments show that our method is compliant with popular learned image coders and vision task models. Under fair comparison, our approach outperforms a baseline method by a) more than 3% top-1 accuracy for compressed domain classification, and b) more than 7% mIoU for compressed domain semantic segmentation, at various data rates.
Video captioning is a challenging task as it needs to accurately transform visual understanding into natural language description. To date, state-of-the-art methods inadequately model global-local vision representation for sentence generation, leaving plenty of room for improvement. In this work, we approach the video captioning task from a new perspective and propose a GLR framework, namely a global-local representation granularity. Our GLR demonstrates three advantages over the prior efforts. First, we propose a simple solution, which exploits extensive vision representations from different video ranges to improve linguistic expression. Second, we devise a novel global-local encoder, which encodes different video representations including long-range, short-range and local-keyframe, to produce rich semantic vocabulary for obtaining a descriptive granularity of video contents across frames. Finally, we introduce the progressive training strategy which can effectively organize feature learning to incur optimal captioning behavior. Evaluated on the MSR-VTT and MSVD dataset, we outperform recent state-of-the-art methods including a well-tuned SA-LSTM baseline by a significant margin, with shorter training schedules. Because of its simplicity and efficacy, we hope that our GLR could serve as a strong baseline for many video understanding tasks besides video captioning. Code will be available.
The outbreak of coronavirus disease (COVID-19) has been a nightmare to citizens, hospitals, healthcare practitioners, and the economy in 2020. The overwhelming number of confirmed cases and suspected cases put forward an unprecedented challenge to the hospital’s capacity of management and medical resource distribution. To reduce the possibility of cross-infection and attend a patient according to his severity level, expertly diagnosis and sophisticated medical examinations are often required but hard to fulfil during a pandemic. To facilitate the assessment of a patient’s severity, this paper proposes a multi-modality feature learning and fusion model for end-to-end covid patient severity prediction using the blood test supported electronic medical record (EMR) and chest computerized tomography (CT) scan images. To evaluate a patient’s severity by the co-occurrence of salient clinical features, the High-order Factorization Network (HoFN) is proposed to learn the impact of a set of clinical features without tedious feature engineering. On the other hand, an attention-based deep convolutional neural network (CNN) using pre-trained parameters are used to process the lung CT images. Finally, to achieve cohesion of cross-modality representation, we design a loss function to shift deep features of both-modality into the same feature space which improves the model’s performance and robustness when one modality is absent. Experimental results demonstrate that the proposed multi-modality feature learning and fusion model achieves high performance in an authentic scenario.
This paper proposes a bio-inspired visual motion estimation algorithm based on motion energy, along with its compact very-large-scale integration (VLSI) architecture using low-cost embedded systems. The algorithm mimics motion perception functions of retina, V1, and MT neurons in a primate visual system. It involves operations of ternary edge extraction, spatiotemporal filtering, motion energy extraction, and velocity integration. Moreover, we propose the concept of confidence map to indicate the reliability of estimation results on each probing location. Our algorithm involves only additions and multiplications during runtime, which is suitable for low-cost hardware implementation. The proposed VLSI architecture employs multiple (frame, pixel, and operation) levels of pipeline and massively parallel processing arrays to boost the system performance. The array unit circuits are optimized to minimize hardware resource consumption. We have prototyped the proposed architecture on a low-cost field-programmable gate array platform (Zynq 7020) running at 53-MHz clock frequency. It achieved 30-frame/s real-time performance for velocity estimation on 160 × 120 probing locations. A comprehensive evaluation experiment showed that the estimated velocity by our prototype has relatively small errors (average endpoint error < 0.5 pixel and angular error < 10°) for most motion cases.
