检索结果-内蒙古大学图书馆

A twofold siamese network for real-time object tracking

学校读者我要写书评

暂无评论

arXiv 2018年

Observing that Semantic features learned in an image classification task and Appearance features learned in a similarity matching task complement each other, we build a twofold Siamese network, named SA-Siam, for real-time object tracking. SA-Siam is composed of a semantic branch and an appearance branch. Each branch is a similarity-learning Siamese network. An important design choice in SA-Siam is to separately train the two branches to keep the heterogeneity of the two types of features. In addition, we propose a channel attention mechanism for the semantic branch. Channel-wise weights are computed according to the channel activations around the target position. While the inherited architecture from SiamFC [3] allows our tracker to operate beyond real-time, the twofold design and the attention mechanism significantly improve the tracking performance. The proposed SA-Siam outperforms all other real-time trackers by a large margin on OTB-2013/50/100 benchmarks. Copyright © 2018, The Authors. All rights reserved.

关键词： Semantics

COOPERATIVE HYBRID DIGITAL-ANALOG VIDEO TRANSMISSION IN D2D NETWORKS

学校读者我要写书评

暂无评论

COOPERATIVE HYBRID DIGITAL-ANALOG VIDEO TRANSMISSION IN D2D ...

IEEE International Conference on Image processing

作者： Jian Shen Fei Liang Chong Luo Houqiang Li Wenjun Zeng CAS Key Laboratory of Technology in Geo-Spatial Information Processing and Application System University of Science and Technology of China Hefei China Microsoft Research Asia Beijing China

In this paper, we propose a cooperative video transmission scheme in D2D networks. This research is motivated by the growing interests in hybrid digital-analog video transmissions and device-to-device (D2D) communications. The framework of D2D communications can be generally modeled as a three-node network. In this network, coset coding is used to allow the destination to exploit the correlations between the video signals received in two phases. We have done some work of further optimization to improve the video quality at destination in this network. First, we derive a closed form of the reconstruction error at the destination. This provides a theoretical foundation for finding the optimal quantization step size in coset coding. Then, based on the accurate analysis on the coset coding we design a new power allocation algorithm. Experimental results verify that our scheme outperforms the recently proposed WCVC and DCVC.

关键词： Encoding Resource management Relays Distortion Quantization (signal) Device-to-device communication Decoding

User specific friend recommendation in social media community

学校读者我要写书评

暂无评论

User specific friend recommendation in social media communit...

IEEE International Conference on Multimedia and Expo (ICME)

作者： Cong Guo Xinmei Tian Tao Mei CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System University of Science and Technology of China Hefei Anhui China Microsoft Research Beijing China

Social networks nowadays have become an important form of communication in which users can post their current status or share their lives by mobile phones or the Web. In this paper, we develop an effective and efficient model to estimate continuous tie strength between users for friend recommendation with the heterogeneous data from social media community. We categorize those multimodal data into two classes: interaction data (e.g., comments, marking favorite photos) and similarity data(e.g., common friends, groups, tags, geo, visual). We propose to use asymmetric relationship in the interaction data for tie strength estimation instead of using the conventional symmetric ones. Furthermore, by exploring the behavior of users in a social media community, we find that the tie strength between users can be approximately modeled as a linear function of their social connections. Based on this observation, we propose an effective and highly efficient user specific linear model for the tie strength estimation. The experiments on a popular social network show promising results and demonstrate the effectiveness of our proposed method.

关键词： Kernel Social network services Visualization Communities Data models Estimation Vectors

Convolutional Neural Network-Based Invertible Half-Pixel Interpolation Filter for Video Coding

学校读者我要写书评

暂无评论

Convolutional Neural Network-Based Invertible Half-Pixel Int...

IEEE International Conference on Image processing

作者： Ning Yan Dong Liu Houqiang Li Tong Xu Feng Wu Bin Li CAS Key Laboratory of Technology in Geo-Spatial Information Processing and Application System University of Science and Technology of China Hefei China Microsoft Research Asia Beijing China

Fractional-pixel interpolation has been widely used in the modern video coding standards to improve the accuracy of motion compensated prediction. Traditional interpolation filters are designed based on the signal processing theory. However, video signal is non-stationary, making the traditional methods less effective. In this paper, we reveal that the interpolation filter can not only generate the fractional pixels from the integer pixels, but also reconstruct the integer pixels from the fractional ones. This property is called invertibility. Inspired by the invertibility of fractional-pixel interpolation, we propose an end-to-end scheme based on convolutional neural network (CNN) to derive the invertible interpolation filter, termed CNNInvIF. CNNlnvIF does not need the “ground-truth” of fractional pixels for training. Experimental results show that the proposed CNNInvIF can achieve up to 4.6% and on average 2.2% BD-rate reduction than HEVC under the low-delay P configuration.

关键词： Interpolation Video coding Training Image reconstruction geometry Convolutional neural networks Image coding

Large Language Models are Good Attackers: Efficient and Stealthy Textual Backdoor Attacks

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Li, Ziqiang Zeng, Yueqi Xia, Pengfei Liu, Lei Fu, Zhangjie Li, Bin Nanjing University of Information Science and Technology China Big Data and Decision Lab University of Science and Technology of China China CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System China

With the burgeoning advancements in the field of natural language processing (NLP), the demand for training data has increased significantly. To save costs, it has become common for users and businesses to outsource the labor-intensive task of data collection to third-party entities. Unfortunately, recent research has unveiled the inherent risk associated with this practice, particularly in exposing NLP systems to potential backdoor attacks. Specifically, these attacks enable malicious control over the behavior of a trained model by poisoning a small portion of the training data. Unlike backdoor attacks in computer vision, textual backdoor attacks impose stringent requirements for attack stealthiness. However, existing attack methods meet significant trade-off between effectiveness and stealthiness, largely due to the high information entropy inherent in textual data. In this paper, we introduce the Efficient and Stealthy Textual backdoor attack method, EST-Bad, leveraging Large Language Models (LLMs). Our EST-Bad encompasses three core strategies: optimizing the inherent flaw of models as the trigger, stealthily injecting triggers with LLMs, and meticulously selecting the most impactful samples for backdoor injection. Through the integration of these techniques, EST-Bad demonstrates an efficient achievement of competitive attack performance while maintaining superior stealthiness compared to prior methods across various text classifier datasets. © 2024, CC BY.

关键词： Deep neural networks

CONVOLUTIONAL NEURAL NETWORK-BASED ARITHMETIC CODING OF DC COEFFICIENTS FOR HEVC INTRA CODING

学校读者我要写书评

暂无评论

CONVOLUTIONAL NEURAL NETWORK-BASED ARITHMETIC CODING OF DC C...

IEEE International Conference on Image processing

作者： Changyue Ma Dong Liu Xiulian Peng Feng Wu CAS Key Laboratory of Technology in Geo-Spatial Information Processing and Application System University of Science and Technology of China Hefei China Microsoft Research Asia Beijing China

In the state-of-the-art video coding standard-High Efficiency Video Coding (HEVC), context-adaptive binary arithmetic coding (CABAC) is adopted as the entropy coding tool. In CABAC, the binarization processes are manually designed, and the context models are empirically crafted, both of which incur that the probability distribution of the syntax elements may not be estimated accurately, and restrict the coding efficiency. In this paper, we adopt a convolutional neural network-based arithmetic coding (CNNAC) strategy, and conduct studies on the coding of the DC coefficients for HEVC intra coding. Instead of manually designing binarization process and context model, we propose to directly estimate the probability distribution of the value of the DC coefficient using densely connected convolutional networks. The estimated probability together with the real DC coefficient are then input into a multi-level arithmetic codec to fulfill entropy coding. Simulation results show that our proposed CNNAC leads to on average 22.47% bits saving compared with CABAC for the bits of DC coefficients, which corresponds to 1.6% BD-rate reduction than the HEVC anchor.

关键词： Context modeling Probability distribution Entropy coding Codecs Training data Tools

A Method for Object Occlusion Handling Based on Multilevel Track Queues

学校读者我要写书评

暂无评论

A Method for Object Occlusion Handling Based on Multilevel T...

International Conference on Multimedia and Signal processing (CMSP)

作者： Biao Jin Wenlong Hu Yu Zhang Institute of Electronic Key Laboratory of Technology in Geo-spatial Information Processing and Application System CAS Graduate School Chinese Academy and Sciences Beijing China Institute of Electronic Key Laboratory of Technology in Geo-spatial Information Processing and Application System Chinese Academy and Sciences Beijing China China Electrical Power Research Institute Beijing China

Multi-object tracking is important in many computer vision applications. The major difficulties are due to inter-object or scene occlusion and data association. In this paper, we present a method to automatically detect and track multiple objects in complicated scenario from a single camera that is stationary. The proposed detecting method can prevent the moving objects updated to the background and can restrain ghosts. The moving objects are modeled fusing the hue and edge features. The system achieves tracking the object using the proposed associated strategy based on multilevel track queues. Experiments show the effectiveness of our approach under different conditions with complete occlusions.

关键词： Tracking Image edge detection Pixel Cameras Videos Computational modeling Algorithm design and analysis

Temporal Context Mining for Learned Video Compression

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Sheng, Xihua Li, Jiahao Li, Bin Li, Li Liu, Dong Lu, Yan The CAS Key Laboratory of Technology in Geo-Spatial Information Processing and Application System University of Science and Technology of China Hefei230027 China Microsoft Research Asia Beijing100080 China

Applying deep learning to video compression has attracted increasing attention in recent few years. In this work, we address end-to-end learned video compression with a special focus on better learning and utilizing temporal contexts. We propose to propagate not only the last reconstructed frame but also the feature before obtaining the reconstructed frame for temporal context mining. From the propagated feature, we learn multi-scale temporal contexts and re-fill the learned temporal contexts into the modules of our compression scheme, including the contextual encoder-decoder, the frame generator, and the temporal context encoder. We discard the parallelizationunfriendly auto-regressive entropy model to pursue a more practical encoding and decoding time. Experimental results show that our proposed scheme achieves a higher compression ratio than the existing learned video codecs. Our scheme also outperforms x264 and x265 (representing industrial software for H.264 and H.265, respectively) as well as the official reference software for H.264, H.265, and H.266 (JM, HM, and VTM, respectively). Specifically, when intra period is 32 and oriented to PSNR, our scheme outperforms H.265-HM by 14.4% bit rate saving;when oriented to MS-SSIM, our scheme outperforms H.266-VTM by 21.1% bit rate saving. Copyright © 2021, The Authors. All rights reserved.

关键词： Image compression

Residual objectness for imbalance reduction

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Chen, Joya Liu, Dong Luo, Bin Peng, Xuezheng Xu, Tong Chen, Enhong Anhui Province Key Laboratory of Big Data Analysis and Application University of Science and Technology of China CAS Key Laboratory of Technology in Geo-Spatial Information Processing and Application System University of Science and Technology of China Tencent TaiQ Team

For a long time, object detectors have suffered from extreme imbalance between foregrounds and backgrounds. While several sampling/reweighting schemes have been explored to alleviate the imbalance, they are usually heuristic and demand laborious hyper-parameters tuning, which is hard to achieve the optimality. In this paper, we first reveal that such the imbalance could be addressed in a learning-based manner. Guided by this illuminating observation, we propose a novel Residual Objectness (ResObj) mechanism that addresses the imbalance by end-to-end optimization, while no further hand-crafted sampling/reweighting is required. Specifically, by applying multiple cascaded objectness-related modules with residual connections, we formulate an elegant consecutive refinement procedure for distinguishing the foregrounds from backgrounds, thereby progressively addressing the imbalance. Extensive experiments present the effectiveness of our method, as well as its compatibility and adaptivity for both region-based and one-stage detectors, namely, the RetinaNet-ResObj, YOLOv3-ResObj and FasterRCNN-ResObj achieve relative 3.6%, 3.9%, 3.2% Average Precision (AP) improvements compared with their vanilla models on COCO, respectively. Copyright © 2019, The Authors. All rights reserved.

关键词： Object detection