arXiv subjects

Jiangtao Wen

Publications and source records attributed to Jiangtao Wen.

27 records · Page 2Linked to original sources

arXiv2020

Online Multi-modal Person Search in Videos

The task of searching certain people in videos has seen increasing potential in real-world applications, such as video organization and editing. Most existing approaches are devised to work in an offline manner, where identities can only be inferred after an entire video is examined. This working manner precludes such methods from being applied to online services or those applications that require real-time responses. In this paper, we propose an online person search framework, which can recognize people in a video on the fly. This framework maintains a multimodal memory bank at its heart as the basis for person recognition, and updates it dynamically with a policy obtained by reinforcement learning. Our experiments on a large movie dataset show that the proposed method is effective, not only achieving remarkable improvements over online schemes but also outperforming offline methods.

cs.CV↗

arXiv2019

A Generalized Rate-Distortion-$λ$ Model Based HEVC Rate Control Algorithm

The High Efficiency Video Coding (HEVC/H.265) standard doubles the compression efficiency of the widely used H.264/AVC standard. For practical applications, rate control (RC) algorithms for HEVC need to be developed. Based on the R-Q, R-$ρ$ or R-$λ$ models, rate control algorithms aim at encoding a video clip/segment to a target bit rate accurately with high video quality after compression. Among the various models used by HEVC rate control algorithms, the R-$λ$ model performs the best in both coding efficiency and rate control accuracy. However, compared with encoding with a fixed quantization parameter (QP), even the best rate control algorithm [1] still under-performs when comparing the video quality achieved at identical average bit rates. In this paper, we propose a novel generalized rate-distortion-$λ$ (R-D-$λ$) model for the relationship between rate (R), distortion (D) and the Lagrangian multiplier ($λ$) in rate-distortion (RD) optimized encoding. In addition to the well designed hierarchical initialization and coefficient update scheme, a new model based rate allocation scheme composed of amortization, smooth window and consistency control is proposed for a better rate allocation. Experimental results implementing the proposed algorithm in the HEVC reference software HM-16.9 show that the proposed rate control algorithm is able to achieve an average of BDBR saving of 6.09%, 3.15% and 4.03% for random access (RA), low delay P (LDP) and low delay B (LDB) configurations respectively as compared with the R-$λ$ model based RC algorithm [1] implemented in HM. The proposed algorithm also outperforms the state-of-the-art algorithms, while rate control accuracy and encoding speed are hardly impacted.

cs.MM↗

arXiv2019

Long and Diverse Text Generation with Planning-based Hierarchical Variational Model

Existing neural methods for data-to-text generation are still struggling to produce long and diverse texts: they are insufficient to model input data dynamically during generation, to capture inter-sentence coherence, or to generate diversified expressions. To address these issues, we propose a Planning-based Hierarchical Variational Model (PHVM). Our model first plans a sequence of groups (each group is a subset of input items to be covered by a sentence) and then realizes each sentence conditioned on the planning result and the previously generated context, thereby decomposing long text generation into dependent sentence generation sub-tasks. To capture expression diversity, we devise a hierarchical latent structure where a global planning latent variable models the diversity of reasonable planning and a sequence of local latent variables controls sentence realization. Experiments show that our model outperforms state-of-the-art baselines in long and diverse text generation.

cs.CL↗

arXiv2018

LSTM-Based Facial Performance Capture Using Embedding Between Expressions

We present a novel end-to-end framework for facial performance capture given a monocular video of an actor's face. Our framework are comprised of 2 parts. First, to extract the information in the frames, we optimize a triplet loss to learn the embedding space which ensures the semantically closer facial expressions are closer in the embedding space and the model can be transferred to distinguish the expressions that are not presented in the training dataset. Second, the embeddings are fed into an LSTM network to learn the deformation between frames. In the experiments, we demonstrated that compared to other methods, our method can distinguish the delicate motion around lips and significantly reduce jitters between the tracked meshes.

cs.GR↗

arXiv2018

Two-pass Light Field Image Compression for Spatial Quality and Angular Consistency

The quality assessment of light field images presents new challenges to conventional compression methods, as the spatial quality is affected by the optical distortion of capturing devices, and the angular consistency affects the performance of dynamic rendering applications. In this paper, we propose a two-pass encoding system for pseudo-temporal sequence based light field image compression with a novel frame level bit allocation framework that optimizes spatial quality and angular consistency simultaneously. Frame level rate-distortion models are estimated during the first pass, and the second pass performs the actual encoding with optimized bit allocations given by a two-step convex programming. The proposed framework supports various encoder configurations. Experimental results show that comparing to the anchor HM 16.16 (HEVC reference software), the proposed two-pass encoding system on average achieves 11.2% to 11.9% BD-rate reductions for the all-intra configuration, 15.8% to 32.7% BD-rate reductions for the random-access configuration, and 12.1% to 15.7% BD-rate reductions for the low-delay configuration. The resulting bit errors are limited, and the total time cost is less than twice of the one-pass anchor. Comparing with our earlier low-delay configuration based method, the proposed system improves BD-rate reduction by 3.1% to 8.3%, reduces the bit errors by more than 60%, and achieves more than 12x speed up.

cs.MM↗

arXiv2018

Convex Optimization Based Bit Allocation for Light Field Compression under Weighting and Consistency Constraints

Compared with conventional image and video, light field images introduce the weight channel, as well as the visual consistency of rendered view, information that has to be taken into account when compressing the pseudo-temporal-sequence (PTS) created from light field images. In this paper, we propose a novel frame level bit allocation framework for PTS coding. A joint model that measures weighted distortion and visual consistency, combined with an iterative encoding system, yields the optimal bit allocation for each frame by solving a convex optimization problem. Experimental results show that the proposed framework is effective in producing desired distortion distribution based on weights, and achieves up to 24.7% BD-rate reduction comparing to the default rate control algorithm.

cs.MM↗

arXiv2018

A Bayesian Approach to Block Structure Inference in AV1-based Multi-rate Video Encoding

Due to differences in frame structure, existing multi-rate video encoding algorithms cannot be directly adapted to encoders utilizing special reference frames such as AV1 without introducing substantial rate-distortion loss. To tackle this problem, we propose a novel bayesian block structure inference model inspired by a modification to an HEVC-based algorithm. It estimates the posterior probabilistic distributions of block partitioning, and adapts early terminations in the RDO procedure accordingly. Experimental results show that the proposed method provides flexibility for controlling the tradeoff between speed and coding efficiency, and can achieve an average time saving of 36.1% (up to 50.6%) with negligible bitrate cost.

cs.MM↗

arXiv2018

Fast Block Structure Determination in AV1-based Multiple Resolutions Video Encoding

The widely used adaptive HTTP streaming requires an efficient algorithm to encode the same video to different resolutions. In this paper, we propose a fast block structure determination algorithm based on the AV1 codec that accelerates high resolution encoding, which is the bottle-neck of multiple resolutions encoding. The block structure similarity across resolutions is modeled by the fineness of frame detail and scale of object motions, this enables us to accelerate high resolution encoding based on low resolution encoding results. The average depth of a block's co-located neighborhood is used to decide early termination in the RDO process. Encoding results show that our proposed algorithm reduces encoding time by 30.1%-36.8%, while keeping BD-rate low at 0.71%-1.04%. Comparing to the state-of-the-art, our method halves performance loss without sacrificing time savings.

cs.MM↗

arXiv2015

Are You Really Hidden? Predicting Current City from Profile and Social Relationship

Privacy has become a major concern in Online Social Networks (OSNs) due to threats such as advertising spam, online stalking and identity theft. Although many users hide or do not fill out their private attributes in OSNs, prior studies point out that the hidden attributes may be inferred from some other public information. Thus, users' private information could still be at stake to be exposed. Hitherto, little work helps users to assess the exposure probability/risk that the hidden attributes can be correctly predicted, let alone provides them with pointed countermeasures. In this article, we focus our study on the exposure risk assessment by a particular privacy-sensitive attribute - current city - in Facebook. Specifically, we first design a novel current city prediction approach that discloses users' hidden `current city' from their self-exposed information. Based on 371,913 Facebook users' data, we verify that our proposed prediction approach can predict users' current city more accurately than state-of-the-art approaches. Furthermore, we inspect the prediction results and model the current city exposure probability via some measurable characteristics of the self-exposed information. Finally, we construct an exposure estimator to assess the current city exposure risk for individual users, given their self-exposed information. Several case studies are presented to illustrate how to use our proposed estimator for privacy protection.

cs.SI↗