Search Results for author: Zhenzhong Chen

Found 25 papers, 9 papers with code

Deep Deconfounded Content-based Tag Recommendation for UGC with Causal Intervention

1 code implementation28 May 2022 Yaochen Zhu, Xubin Ren, Jing Yi, Zhenzhong Chen

We first establish a causal graph to represent the relations among uploader, UGC, and tag, where the uploaders are identified as confounders that spuriously correlate UGC and tag selections.

Recommendation Systems TAG

Multi-Auxiliary Augmented Collaborative Variational Auto-encoder for Tag Recommendation

no code implementations20 Apr 2022 Jing Yi, Xubin Ren, Zhenzhong Chen

Recommending appropriate tags to items can facilitate content organization, retrieval, consumption and other applications, where hybrid tag recommender systems have been utilized to integrate collaborative information and content information for better recommendations.

Recommendation Systems TAG

Pyramid Feature Alignment Network for Video Deblurring

no code implementations28 Mar 2022 Leitian Tao, Zhenzhong Chen

To better handle the challenges of complex and large motions, instead of aligning features at each scale separately, lower-scale motion information is used to guide the higher-scale motion estimation.

Deblurring Motion Estimation

Deep Causal Reasoning for Recommendations

1 code implementation6 Jan 2022 Yaochen Zhu, Jing Yi, Jiayi Xie, Zhenzhong Chen

As with all observational studies, hidden confounders, which are factors that affect both item exposures and user ratings, lead to a systematic bias in the estimation.

Recommendation Systems Variational Inference

Object-Relation Reasoning Graph for Action Recognition

no code implementations CVPR 2022 Yangjun Ou, Li Mi, Zhenzhong Chen

By combining an object-level graph (OG) and a relation-level graph (RG), the proposed OR2G catches the attribute transitions of objects and reasons about the relationship transitions between objects simultaneously.

Action Recognition

Make It Move: Controllable Image-to-Video Generation with Text Descriptions

1 code implementation CVPR 2022 Yaosi Hu, Chong Luo, Zhenzhong Chen

With both controllable appearance and motion, TI2V aims at generating videos from a static image and a text description.

Video Generation

Optical-Flow-Reuse-Based Bidirectional Recurrent Network for Space-Time Video Super-Resolution

no code implementations13 Oct 2021 Yuantong Zhang, Huairui Wang, Zhenzhong Chen

To solve the above problem of the existing methods, we propose a coarse-to-fine bidirectional recurrent neural network instead of using ConvLSTM to leverage knowledge between adjacent frames.

Optical Flow Estimation Space-time Video Super-resolution +1

Cross-modal Variational Auto-encoder for Content-based Micro-video Background Music Recommendation

no code implementations15 Jul 2021 Jing Yi, Yaochen Zhu, Jiayi Xie, Zhenzhong Chen

Moreover, the multimodal information is fused by the product-of-experts (PoE) principle, where the semantic information in visual and textual modalities of the micro-video are weighted according to their variance estimations such that the modality with a lower noise level is given more weights.

Predicate correlation learning for scene graph generation

no code implementations6 Jul 2021 Leitian Tao, Li Mi, Nannan Li, Xianhang Cheng, Yaosi Hu, Zhenzhong Chen

For a typical Scene Graph Generation (SGG) method, there is often a large gap in the performance of the predicates' head classes and tail classes.

Graph Generation Scene Graph Generation

Visual Relationship Forecasting in Videos

no code implementations2 Jul 2021 Li Mi, Yangjun Ou, Zhenzhong Chen

To evaluate the VRF task, we introduce two video datasets named VRF-AG and VRF-VidOR, with a series of spatio-temporally localized visual relation annotations in a video.

Decision Making

Variational Bandwidth Auto-encoder for Hybrid Recommender Systems

1 code implementation17 May 2021 Yaochen Zhu, Zhenzhong Chen

Moreover, by considering the fusion of collaborative and feature variables as a virtual communication channel from an information-theoretic perspective, we introduce a user-dependent channel to dynamically control the information allowed to be accessed from the feature embeddings.

Recommendation Systems

Towards Visual Distortion in Black-Box Attacks

1 code implementation21 Jul 2020 Nannan Li, Zhenzhong Chen

Constructing adversarial examples in a black-box threat model injures the original images by introducing visual distortion.

Perceptual Distance

Multiple Video Frame Interpolation via Enhanced Deformable Separable Convolution

1 code implementation15 Jun 2020 Xianhang Cheng, Zhenzhong Chen

During the learning process, different intermediate time step can be involved as a control variable by means of an extension of coord-conv trick, allowing the estimated components to vary with different input temporal information.

Motion Estimation Optical Flow Estimation +1

Towards Mesh Saliency Detection in 6 Degrees of Freedom

no code implementations27 May 2020 Xiaoying Ding, Zhenzhong Chen

Traditional 3D mesh saliency detection algorithms and corresponding databases were proposed under several constraints such as providing limited viewing directions and not taking the subject's movement into consideration.

Saliency Detection

Predicting the Popularity of Micro-videos with Multimodal Variational Encoder-Decoder Framework

1 code implementation28 Mar 2020 Yaochen Zhu, Jiayi Xie, Zhenzhong Chen

As an emerging type of user-generated content, micro-video drastically enriches people's entertainment experiences and social interactions.

Learning Compact Reward for Image Captioning

no code implementations24 Mar 2020 Nannan Li, Zhenzhong Chen

Adversarial learning has shown its advances in generating natural and diverse descriptions in image captioning.

Image Captioning reinforcement-learning

Learned Image Downscaling for Upscaling using Content Adaptive Resampler

3 code implementations22 Jul 2019 Wanjie Sun, Zhenzhong Chen

The proposed resampler network generates content adaptive image resampling kernels that are applied to the original HR input to generate pixels on the downscaled image.

Image Super-Resolution

Obj-GloVe: Scene-Based Contextual Object Embedding

no code implementations2 Jul 2019 Canwen Xu, Zhenzhong Chen, Chenliang Li

Recently, with the prevalence of large-scale image dataset, the co-occurrence information among classes becomes rich, calling for a new way to exploit it to facilitate inference.

Dimensionality Reduction Image Generation +2

A Review-Driven Neural Model for Sequential Recommendation

no code implementations1 Jul 2019 Chenliang Li, Xichuan Niu, Xiangyang Luo, Zhenzhong Chen, Cong Quan

Given a sequence of historical purchased items for a user, we devise a novel hierarchical attention over attention mechanism to capture sequential patterns at both union-level and individual-level.

Collaborative Filtering Sequential Recommendation

Macroblock Classification Method for Video Applications Involving Motions

no code implementations28 Feb 2015 Weiyao Lin, Ming-Ting Sun, Hongxiang Li, Zhenzhong Chen, Wei Li, Bing Zhou

We demonstrate that this low-computation-complexity method can efficiently catch the characteristics of the frame.

Change Detection Classification +2

A Heat-Map-based Algorithm for Recognizing Group Activities in Videos

no code implementations21 Feb 2015 Weiyao Lin, Hang Chu, Jianxin Wu, Bin Sheng, Zhenzhong Chen

In this paper, a new heat-map-based (HMB) algorithm is proposed for group activity recognition.

Group Activity Recognition

Intra-and-Inter-Constraint-based Video Enhancement based on Piecewise Tone Mapping

no code implementations21 Feb 2015 Yuanzhe Chen, Weiyao Lin, Chongyang Zhang, Zhenzhong Chen, Ning Xu, Jun Xie

In this paper, we propose a new intra-and-inter-constraint-based video enhancement approach aiming to 1) achieve high intra-frame quality of the entire picture where multiple region-of-interests (ROIs) can be adaptively and simultaneously enhanced, and 2) guarantee the inter-frame quality consistencies among video frames.

Tone Mapping Video Enhancement

Cannot find the paper you are looking for? You can Submit a new open access paper.