34 accepted papers
Traditional image compression prioritizes pixel fidelity but often preserves details irrelevant to downstream vision tasks. Compressing task-specific representations instead better aligns with task semantics, yet redundant information persists across correlated tasks. Existing multi-task compression
Learned lossless image compression has achieved significant advancements in recent years. However, existing methods often rely on training amortized generative models on massive datasets, resulting in sub-optimal probability distribution estimation for specific testing images during encoding process…
Video compression is a fundamental topic in the visual intelligence, bridging visual signal sensing/capturing and high-level visual analytics. The broad success of artificial intelligence (AI) technology has enriched the horizon of video compression into novel paradigms by leveraging end-to-end opti
To ensure system responsiveness, some compute-intensive tasks are usually offloaded to cloud or edge computing devices. In environments where connection to external computing facilities is unavailable, computation offloading among members within an autonomous multi-robot system (AMRS) becomes a solu
In this paper, a novel Diffusion-based 3D Pose estimation (D3DP) method with Joint-wise reProjection-based Multi-hypothesis Aggregation (JPMA) is proposed for probabilistic 3D human pose estimation. On the one hand, D3DP generates multiple possible 3D pose hypotheses for a single 2D observation. It…
Quantization is an effective way to reduce the memory and computational costs of deep neural networks in which the full-precision weights and activations are represented using low-bit values. The bit-width for each layer in most of existing quantization methods is static, i.e., the same for all samp…
"This paper introduces a novel Pre-trained Spatial Temporal Many-to-One (P-STMO) model for 2D-to-3D human pose estimation task. To reduce the difficulty of capturing spatial and temporal information, we divide this task into two stages: pre-training (Stage I) and fine-tuning (Stage II). In Stage I,…
Although many video prediction methods have obtained good performance in low-resolution (64 128) videos, predictive models for high-resolution (512 4K) videos have not been fully explored yet, which are more meaningful due to the increasing demand for high-quality videos. Compared with low-resolutio…
We propose an end-to-end image compression and analysis model with Transformers, targeting to the cloud-based image classification application. Instead of placing an existing Transformer-based image classification model directly after an image codec, we aim to redesign the Vision Transformer (ViT) m…
As depth maps show unique characteristics like piecewise smooth regions bounded by sharp edges at depth discontinuities, new coding tools are required to approximate these signal characteristics. Moreover, the number of bits to signal the residual values for each segment can be further reduced by in…
Quantization is an effective way for reducing the memory and computation costs of deep neural networks. Most of existing methods exploit the fixed-precision quantization approach, e.g., weights and activations (i.e., output features) are represented as 8-bit values. Although mixed-precision quantiza…
Accurately predicting inter-frame motion information plays a key role in video prediction tasks. In this paper, we propose a Motion-Aware Unit (MAU) to capture reliable inter-frame motion information by broadening the temporal receptive field of the predictive units. The MAU consists of two modules,…
Recently, transformer has achieved remarkable performance on a variety of computer vision applications. Compared with mainstream convolutional neural networks, vision transformers are often of sophisticated architectures for extracting powerful feature representations, which are more difficult to be…
As the computing power of modern hardware is increasing strongly, pre-trained deep learning models (e.g., BERT, GPT-3) learned on large-scale datasets have shown their effectiveness over conventional methods. The big progress is mainly contributed to the representation ability of transformer and its…
Unsupervised learning methods have recently shown their competitiveness against supervised training. Typically, these methods use a single objective to train the entire network. But one distinct advantage of unsupervised over supervised learning is that the former possesses more variety and freedom…
Transformers are powerful for sequence modeling. Nearly all state-of-the-art language models and pre-trained language models are based on the Transformer architecture. However, it distinguishes sequential tokens only with the token position index. We hypothesize that better contextual representation…
Due to the widespread deployment of fingerprint/face/speaker recognition systems, attacking deep learning based biometric systems has drawn more and more attention. Previous research mainly studied the attack to the vision-based system, such as fingerprint and face recognition. While the attack for…
This paper proposes the Global-Local Temporal Representation (GLTR) to exploit the multi-scale temporal cues in video sequences for video person Re-Identification (ReID). GLTR is constructed by first modeling the short-term temporal cues among adjacent frames, then capturing the long-term relations…
To tackle three main problems in depth map super resolution (SR) process, which are texture copy artifacts, blurred edge artifacts and jagged edge artifacts, we propose a depth map super resolution with denoising method based on multiscale directional fusion via nonsubsampled contourlet transform (N…
Graph sampling with noise is a fundamental problem in graph signal processing (GSP). Previous works assume an unbiased least square (LS) signal reconstruction scheme and select samples greedily via expensive extreme eigenvector computation. A popular biased scheme using graph Laplacian regularizatio…
Existing methods for image captioning are usually trained by cross entropy loss, which leads to exposure bias and the inconsistency between the optimizing function and evaluation metrics. Recently it has been shown that these two issues can be addressed by incorporating techniques from reinforcement…
Blind image deblurring, i.e., deblurring without knowledge of the blur kernel, is a highly ill-posed problem. The problem can be solved in two parts: i) estimate a blur kernel from the blurry image, and ii) given estimated blur kernel, de-convolve blurry input to restore the target image. In this pa…
Point cloud has attracted more and more attention in 3D object representation, especially in free-view rendering. However, it is challenging to efficiently deploy the point cloud due to its huge data amount with multiple attributes including coordinates, normal and color. In order to represent point…
As compared with traditional video retargeting, stereo video retargeting poses new challenges because stereo video contains the depth information of salient objects and its time dynamics. In this work, we propose a depth-aware stereo video retargeting method by imposing the depth fidelity constrain…
Although the performance of person Re-Identification (ReID) has been significantly boosted, many challenging issues in real scenarios have not been fully investigated, e.g., the complex scenes and lighting variations, viewpoint and pose changes, and the large number of identities in a camera network…
In video decoder applications, motion compensation (MC) is bandwidth consuming because of the non-regular memory access. Especially with the popularity of UHD video and the development of new coding standard (HEVC), external memory bandwidth becomes a crucial bottleneck. In this paper, we propose an…
Input binarization has shown to be an effective way for network acceleration. However, previous binarization scheme could be regarded as simple pixel-wise thresholding operations (i.e., order-one approximation) and suffers a big accuracy loss. In this paper, we propose a high-order binarization sche…
Feature extraction and matching are two crucial components in person Re-Identification (ReID). The large pose deformations and the complex view variations exhibited by the captured person images significantly increase the difficulty of learning and matching of the features from person images. To ove…
In this paper, we propose a novel image coding and transmission scheme called AnalogCast, which is a pseudo analog coding system for transmitting satellite remote-sensing images to large number of receivers. AnalogCast follows the idea originally developed for SoftCast [1-3] but with two special tec…
Contexts are crucial for action recognition in video. Current methods often mine contexts after extracting hierarchical local features and focus on their high-order encodings. This paper instead explores contexts as early as possible and leverages their evolutions for action recognition. In particul…
The iterations of many sparse estimation algorithms are comprised of a fixed linear filter cascaded with a thresholding nonlinearity, which collectively resemble a typical neural network layer. Consequently, a lengthy sequence of algorithm iterations can be viewed as a deep network with shared, han…
Background Subtraction (BS) is one of the key steps in video analysis. Many background models have been proposed and achieved promising performance on public data sets. However, due to challenges such as illumination change, dynamic background etc. the resulted foreground segmentation often consists…
This paper proposes a new image denoising approach using adaptive signal modeling and adaptive soft-thresholding. It improves the image quality by regularizing all the patches in image based on distribution modeling in transform domain. Instead of using a global model for all patches, it employs con…
We propose a novel Multi-Task Learning with Low Rank Attribute Embedding (MTL-LORAE) framework for person re-identification. Re-identifications from multiple cameras are regarded as related tasks to exploit shared information to improve re-identification accuracy. Both low level features and semanti…