Artificial Fingerprinting (AF or the so-called digital watermarking) is a technique that can be used to conduct Deepfake attribution by ensuring media authenticity. However, AF does not prioritize its robustness to certain kinds of distortions, making the embedded watermarks vulnerable to some standard image processing operations. Insufficient robustness reduces the practicality of digital watermarking techniques. To address this issue, we propose an enhanced distortion agnostic artificial fingerprinting (EDA-AF) framework which introduces a novel noise layer consisting of an attack booster followed by a convolutional network-based attacker. The attacker simulates various distortions by exploiting adversarial learning with AF for distortion agnostic robustness. Meanwhile, due to the modeling limitation of the convolutional network, we also employ the attack booster to apply a set of differentiable image distortions which cannot be well simulated by the attacker. Extensive experimental results show that the proposed approach improves the quality of the extracted fingerprints. EDA-AF can improve the bitwise accuracy by up to 36%, which takes another step forward on the road of Deepfake attribution.

JPEG has been a widely used lossy image compression codec for nearly three decades. The JPEG standard allows to use customized quantization table; however, it's still a challenging problem to find an optimal quantization table within acceptable computational cost. This work tries to solve the dilemma of balancing between computational cost and image specific optimality by introducing a new concept of texture mosaic images. Instead of optimizing a single image or a collection of representative images, the simulated annealing technique is applied to texture mosaic images to search for an optimal quantization table for each texture category. We use pre-trained VGG-16 CNN model to learn those texture features and predict the new image's texture distribution, then fuse optimal texture tables to come out with an image specific optimal quantization table. On the Kodak dataset with the quality setting Q=95, our experiment shows a size reduction of 23.5% over the JPEG standard table with a slightly 0.35% FSIM decrease, which is visually unperceivable. The proposed JQF method achieves per image optimality for JPEG encoding with less than one second additional timing cost.

3D HEVC is one of the extensions of HEVC (High Efficiency Video Coding), which is the latest video coding standard developed by the Joint Collaborative Team on Video Coding (JCT-VC). The inherent high computing complexity of 3D HEVC handicaps its usage in practical applications. HEVC replaces the macroblock (MB) of H.264 with the largest coding unit (LCU), in which coding units (CUs) of sizes 64 × 64, 32 × 32, 16 × 16, or 8 × 8 pixels are used to build a coding tree unit (CTU). HEVC encoder will traverse the coding modes from the root (the coding level is 0) to the leaves (the coding level is 3) of the CTU. As a result, how to accelerate the encoding process of 3D HEVC with negligible loss of coding efficiency is a hot research topic in the field of video coding. Figure 1 shows the coding level distributions of I04 and I14, where Ikj represents the j-th frame in the k-th GOP. The POC's (picture order counts) of the two frame are P(I04) = 4 and P(I14) = 12 when GOP size is 8. From Figure 1 we observed that, in B-slices, the distributions of "optimal coding level = zero" for adjacent GOP's are almost the same. We found that the required coding level will be similar when the two CUs have similar depth values. We utilize this correlation to limit the required coding level visiting of a given CU which accelerates the encoding process. In this paper, a fast mode decision algorithm for 3D HEVC, based on the depth information related coding mode similarity, is proposed. According to the experimental results, the proposed algorithm can reduce up to 72% executing time of the overall encoding process, while the loss in coding efficiency is negligible.

The objective approaches of 3D image quality assessment play a key role in the development of compression standards and various 3D multimedia applications. The quality assessment of 3D images faces many new challenges, e.g. asymmetric stereo compression, depth perception, and virtual view synthesis, as compared with its 2D counterparts. Moreover, the widely used 2D image quality metric (e.g. PSNR) cannot be directly applied to deal with these newly introduced challenges. This statement can be verified by the low correlation between the computed objective measures and the subjectively measured mean opinion scores (MOS), when 3D images are the tested targets. In order to meet these challenges, in this work, besides traditional 2D image metrics, two binocular behaviors - the binocular combination and the Binocular Frequency Integration (BFI), are utilized as the bases for measuring the quality of stereoscopic 3D images. The effectiveness of BFI-based metrics is verified by conducting subjective evaluations on a publicly available stereo image dataset. Experimental results show that significant consistency could be reached between the measured MOS and the BFI-based metrics, in which the correlation coefficient between them can go up to 0.89 even if the stereo images have been asymmetrically HEVC compressed. Based on the proposed quality metric, we find that asymmetric-stereo compression schemes outperform the corresponding symmetric ones in high bit rate scenarios, which opens up a new research direction for 3D stereo image/video compression studies.

This work addresses the data representation and the compression issues of angular disparity map following the way of HVS to perceive depth information. The continued fraction is utilized to represent the angular disparity map which enables the use of the state-of-the-art video codec (e.g. HEVC) to compress the data directly and maintains quality scalability properties. We observe that there is a non-monotonic phenomenon of the RD curves by applying HEVC compression to angular disparity map directly. This implies that the correlations among inter-layer (i.e., the neighboring integers in (2)) do not follow the traditional models of normal 2D video codecs. Of course, the detailed relationship between the sensitivities and the quantization errors of the newly proposed representation needs in depth further derivations. There are many interesting research issues may be introduced by the proposed data format (e.g., the sensitivities to quantization errors of θ and the rate-distortion optimization scheme for θ) which will, of course, be the research topics of our future work. We expect this work can be a bridge to connect the 3D perception and the 3D compression research fields.

Summary form only given. Distributed video coding (DVC) has been intensively studied in recent years. This new coding paradigm substantially differs from conventional prediction-based video codecs such as MPEG and H.26x, which are characterized by a complex encoder and simple decoder. The conventional DVC codec, e.g., DISCOVER codec, uses advanced frame interpolation techniques to create SI based on adjacent decoded reference frames. The quality of SI is a well-recognized factor in the RD performance of WZ video coding. A high SI quality implies a high correlation between the created SI and the original WZ frame, which then decreases the rate required to achieve a given decoded quality. Clearly, the performance of an SI creation process based on adjacent previously decoded frames is limited by the quality of the past and the future reference frames as well as the distance and motion behavior between them. The correlation between high-motion frames is low and vice versa. That is, SI quality in the conventional codecs depends on the temporal correlation of key frames, which affects the bitrate and PSNR of the compression process. In this work, a novel DVC architecture for dealing with the cases of high-motion and large GOP-size sequences is proposed to better the rate-distortion (RD) performance. For high-motion video sequences, the proposed architecture generates SI by using subsampled spatial information instead of interpolated temporal information. the proposed approach separates the video sequence into subsampled key frames and corresponding WZ frames, which changes the creation of SI. That is, all successive frames on the encoder side are downsized to sub-frames, which are then compressed by an H.264/AVC intra encoder. Experimental results reveal that the subsampling input based DVC codec can gain up to 1.47 dB in the RD measures and maintains the most important characteristic of the DVC codec, the encoder is lightweight, as compared with the conventional WZ codec, respectively. The novel DVC architecture evaluated in this study exploits spatial relations to create SI. The experimental results confirm that the RD performance of the proposed approach is superior to that of the conventional one for high-motion and/or large GOP-size sequences. The quality of spatial interpolation based SI is higher than that of the temporal interpolation one, which leads to a high-PSNR reconstructed WZ frame. The subsampled key frames are also decoded by LDPCA decoder to recover the information lost when H.264/AVC intra coding is used to increase PSNR gain. Since many spatial domain interpolation and super resolution schemes have been proposed for use in the fields of image processing and computer vision, the performance of the proposed DVC codec can be further enhanced by using better schemes to generate even better SI.

Term suggestions recommend query terms to a user based on his initial query. Suggesting adequate terms is a challenging issue. Most existing commercial search engines suggest search terms based on the frequency of prior used terms that match the leading alphabets the user types. In this article, we present a novel mechanism to construct semantic term-relation graphs to suggest relevant search terms in the semantic level. We built term-relation graphs based on multipartite networks of existing social media, especially from Wikipedia. The multipartite linkage networks of contributor-term, term-category, and term-term are extracted from Wikipedia to eventually form term relation graphs. For fusing these multipartite linkage networks, we propose to incorporate the contributor-category networks to model the expertise of the contributors. Based on our experiments, this step has demonstrated clear enhancement on the accuracy of the inferred relatedness of the term-semantic graphs. Experiments on keyword-expanded search based on 200 TREC-5 ad-hoc topics showed obvious advantage of our algorithms over existing approaches.

On the basis of a non-local means denosing process, a novel progressive side information refinement framework for a transform domain Wyner-Ziv video codec is proposed, where the side information is progressively improved, as the decoding proceeds, by exploring both temporal-spatial similarities and already decoded DCT bands. Simulation results show up to 2.5dB in RD performance gain against that of the same codec without including the proposed side information refinement framework for sequences with high motion and/or large group-of-picture sizes. Moreover, the proposed framework adds no significant complexity to the decoder, and even results in a decoding speed-up due to the less required error correcting iterations, for most of the test sequences.

In recommendation systems, a central host typically requires access to user profiles in order to generate useful recommendations. This access, however, undermines user privacy; the more information is revealed to the host, the more the user's privacy is compromised. In this paper, we propose a novel end-to-end encrypted recommendation mechanism which encrypts sensitive private data at the user end, without ever exposing plaintext private data to the host server. Unlike previously proposed privacy-preserving recommendation mechanisms, the data in this proposed system are lossless - a pivotal feature to many applications, e.g., in health informatics, business analytics, cyber security, etc. We achieve this goal by developing encrypted-domain polynomial ring homomorphism cryptographic algorithms to compute similarity of encrypted scores on the server, so that collaborative recommendations can be computed in the encryption domain and only an authorized person can decrypt the exact results. We also propose a novel key management system to make sure private information retrieval and recommendation computations can be executed in the encrypted domain in practice. Our experiments show that the proposed scheme offers robust security and lossless accurate recommendation, as well as high efficiency. Our preliminary results show the recommendation accuracy is 21% better than the existing statistical lossy privacy-preserving mechanisms based on random perturbation and user profile distribution. This new approach can potentially be applied to various data mining and cloud computing environments and significantly alleviates the privacy concerns of users.

Summary form only given. In this work, we experimented on the compression efficiency of rendering lossless compression of depth images and found that the compression ratios can go up to 20.51 and 40 for Interview and Breakdancer test images, respectively, even if the parameter setting is in the worst case (i.e., set fdensity(Znear, Zfar) to its maximum value). This work is our first step toward exploring the performance of rendering lossless compression. It is our belief that, besides the rendering lossless quantization, there are a lot of different issues of depth image compression which are worthy of further exploitation.

Summary form only given. In this paper, Wyner-Ziv (WZ) video coding is a particular case of distributed video coding (DVC). Although some works, with improved performance, have been made in recent years, the coding efficiency of state-of-the-art WZ codec is still far from that of the state-of-the-art prediction-based codec, especially for high and complex motion contents. Moreover, most reported WZ codecs have a high time delay in decoder, which hinders its practical application in real-time systems. The performance of the SI creation process based on adjacent previously decoded frames is limited by the quality of the past and the future reference frames as well as the distance and motion behavior between them. In this work, by combining coding tools developed in recent literatures on transform domain WZ coding with some newly developed modules on both encoding and decoding sides, an efficient and practical WZ video coding architecture, dubbed as Distributed video coding with PArallelized design for Concurrent computing (DISPAC), is proposed to better the rate-distortion (RD) performance. Another unique feature of DISPAC, lies in the parallelizability of the modules used by its WZ decoder which increased the decoding speed largely. Experimental results conducted on a concurrent computing environment (consisting of multi-core CPU and GPU processors) reveal that DISPAC codec can gain up to 2.8 dB in the RD measures and 14.35 times faster in the decoding speed as compared with the-state-of-art WZ video codec, respectively. By shifting the computational complexity from the encoder to the decoder and integrating with appropriate trascoding techniques, DVC has been expected to provide a video codec solution for Cloud computing mobile devices (such as mobile phones).

This paper proposes an effective approach to provide relevant search terms for conceptual Web search. 'Semantic Term Suggestion' function has been included so that users can find the most appropriate query term to what they really need. Conventional approaches for term suggestion involve extracting frequently occurring key terms from retrieved documents. They must deal with term extraction difficulties and interference from irrelevant documents. In this paper, we propose a semantic term suggestion function called Collective Intelligence based Term Suggestion (CITS). CITS provides a novel social-network based framework for relevant terms suggestion with a semantic graph of the search term without limiting to the specific query term. A visualization of semantic graph is presented to the users to help browsing search results from related terms in the semantic graph. The search results are ranked each time according to their relevance to the related terms in the entire query session. Comparing to two popular commercial search engines, a user study of 18 users on 50 search terms showed better user satisfactions and indicated the potential usefulness of proposed method in real-world search applications.

In this paper, we propose a Collaborative Knowledge Semantic Graphs Image Search (CKSGIS) system. It provides a novel way to conduct image search by utilizing the collaborative nature in Wikipedia and by performing network analysis to form semantic graphs for search-term expansion. The collaborative article editing process used by Wikipedia's contributors is formalized as bipartite graphs that are folded into networks between terms. When a user types in a search term, CKSGIS automatically retrieves an interactive semantic graph of related terms that allow users to easily find related images not limited to a specific search term. Interactive semantic graph then serve as an interface to retrieve images through existing commercial search engines. This method significantly saves users' time by avoiding multiple search keywords that are usually required in generic search engines. It benefits both naïve users who do not possess a large vocabulary and professionals who look for images on a regular basis. In our experiments, 85% of the participants favored CKSGIS system rather than commercial search engines.