Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks163 from public data
- 204
- 157
- FBSNet: A Fast Bilateral Symmetrical Network for Real-Time Semantic Segmentation154
This article proposes a Fast Bilateral Symmetrical Network (FBSNet), a symmetrical encoder-decoder structure with two branches, semantic information branch and spatial detail branch that can strike a good balance between accuracy and efficiency.
- MSCFNet: A Lightweight Network With Multi-Scale Context Fusion for Real-Time Semantic Segmentation146
A novel lightweight network using a multi-scale context fusion (MSCFNet) scheme, which explores an asymmetric encoder-decoder architecture to alleviate the trade-off between accuracy, inference speed, and model size.
- Deep Knowledge Tracing and Dynamic Student Classification for Knowledge Tracing146
A novel model for knowledge tracing is proposed that captures students' learning ability and dynamically assigns students into distinct groups with similar ability at regular time intervals and combines this information with a Recurrent Neural Network architecture known as Deep Knowledge Tracing.
- Feature Distillation Interaction Weighting Network for Lightweight Image Super-resolution122
This work proposes a lightweight yet efficient Feature Distillation Interaction Weighted Network (FDIWN), which utilizes a series of specially designed Feature Shuffle Weighted Groups as the backbone, and several novel mutual Wide-residual Distillation interaction Blocks form an FSWG.
- Deep Cross-Modal Correlation Learning for Audio and Lyrics in Music Retrieval113
This is the first study that uses deep architectures for learning the temporal correlation between audio and lyrics, involving two-branch deep neural networks for audio modality and text modality (lyrics) and two significant contributions are made in the audio branch.
- Category-Based Deep CCA for Fine-Grained Venue Discovery From Multimodal Data110
A novel deep learning model, category-based deep canonical correlation analysis, which outperforms state of the arts for cross-modal retrieval between image and text and builds a new venue-aware multimodal data set by integrating Wikipedia featured articles and Foursquare venue photographs.
- 87
- 84
- Leveraging multimodal information for event summarization and concept-level sentiment analysis73
This work presents the EventBuilder system that deals with semantics understanding and automatically generates a multimedia summary for a given event in real-time by leveraging different social media such as Wikipedia and Flickr, and the EventSensor system that aims to address sentics understanding and produces a multimedia Summary for agiven mood.
- End-to-End Named Entity Recognition from English Speech72
A first publicly available NER annotated dataset for English speech is introduced and an E2E approach, which jointly optimizes the ASR and NER tagger components is presented, which outperforms the classical two-step approach.
- ADVISOR72
A fast and effective heuristic ranking approach based on heterogeneous late fusion by jointly considering three aspects: venue categories, visual scene, and user listening history that recommends appealing soundtracks for UGVs to enhance the viewing experience is proposed.
- Deep Triplet Neural Networks with Cluster-CCA for Audio-Visual Cross-Modal Retrieval64
A better representation by constructing a deep triplet neural network with triplet loss for optimal projections can be generated to maximize correlation in the shared subspace and positive examples and negative examples are used in the learning stage to improve the capability of embedding learning between audio and video.
- Context-Patch Face Hallucination Based on Thresholding Locality-Constrained Representation and Reproducing Learning62
This paper incorporates the contextual information of the image patch and proposes a powerful and efficient context-patch-based face hallucination approach, namely, thresholding locality-constrained representation and reproducing learning (TLcR-RL).
- Constructing multilayer locality-constrained matrix regression framework for noise robust face super-resolution58
An efficient multilayer locality-constrained matrix regression (MLCMR) framework to learn the representation of the input LR patch and meanwhile preserve the manifold of the original HR space and aims at reducing the inconsistency gap between different manifolds.
- Hierarchical Deep CNN Feature Set-Based Representation Learning for Robust Cross-Resolution Face Recognition57
A feature set-based representation learning (FSRL) scheme to collaboratively represent the hierarchical features for more accurate recognition and the superiority of the presented algorithm to the other competitive CRFR approaches is verified.
- 56
- Deep CNN Denoiser and Multi-layer Neighbor Component Embedding for Face Hallucination56
This paper proposes a general face hallucination method that can integrate model-based optimization and discriminative inference, and develops a high-frequency details compensation method by dividing the face image to facial components and performing face hallucinations in a multi-layer neighbor embedding manner.
- Text2FaceGAN: Face Generation from Fine Grained Textual Descriptions55
This paper generates captions for images in the CelebA dataset by creating an algorithm to automatically convert a list of attributes to a set of captions, and model the highly multi-modal problem of text to face generation as learning the conditional distribution of faces in same latent space.
- Audio-Visual Embedding for Cross-Modal Music Video Retrieval through Supervised Deep CCA51
This work proposes a novel audio-visual embedding algorithm by Supervised Deep Canonical Correlation Analysis (S-DCCA) that projects audio and video into a shared space to bridge the semantic gap betweenaudio and video and proposes an end-to-end deep model for crossmodal audio- visual learning.
- Cross-resolution face recognition with pose variations via multilayer locality-constrained structural orthogonal procrustes regression48
The proposed MLCSOPR not only learns the pose-robust discriminative representation features to reduce the resolution gap between the LR image space and the high-resolution (HR) one but also strengthens the consistency between theLR and HR image space.
- 40
- LBAN-IL: A novel method of high discriminative representation for facial expression recognition40
A novel LBAN-IL for FER in the wild, including local binary attention network (LBAN) and islets loss (IL), which aims to enhance the discrimination of expression features by increasing the amplitude of vectors.
- TRACE: Linguistic-Based Approach for Automatic Lecture Video Segmentation Leveraging Wikipedia Texts40
- ATLAS40
According to the initial experiments on videos provided by VideoLectures.NET, the proposed algorithm is able to segment and annotate knowledge structures based on fusing temporal transition cues and the evaluation results are very encouraging, which confirms the effectiveness of the ATLAS system.
- PAI-BPR: Personalized Outfit Recommendation Scheme with Attribute-wise Interpretability39
This work solves the problem of interpretability in clothing matching by locating the discordant and harmonious attributes between fashion items and devises an attribute-wise interpretable compatibility scheme with personal preference modelling which captures user-item interaction along with general item- item interaction.
- 38
- Automatic music soundtrack generation for outdoor videos from contextual sensor information37
The experimental results show that the system can successfully create soundtracks that are related to the mood and situation of UGVs and therefore enhance the enjoyment of viewers and is bandwidth efficient since video data does not need to be transmitted for analysis.
- EventBuilder36
The proposed EventBuilder system that enables people to automatically generate a summary for a given event in real-time by visualizing different social media such as Wikipedia and Flickr and efficiently summarizes knowledge structures based on the metadata of photos/videos and Wikipedia articles.
- Camera Network Based Person Re-identification by Leveraging Spatial-Temporal Constraint and Multiple Cameras Relations34
Quantitative experiments conducted on TMin and CamNeT datasets have shown that the proposed probabilistic method achieves a better performance to the novel CNPR problem.
- Videopedia: Lecture Video Recommendation for Educational Blogs Using Topic Modeling33
This work aims to build a system that seamlessly integrates both the text-based blogs and online videos and recommends relevant videos for explaining the concepts given in a blog and uses topic modeling to map videos and blogs in the common semantic space of topics.
- Research on Singing Voice Detection Based on a Long-Term Recurrent Convolutional Network with Vocal Separation and Temporal Smoothing31
A long-term recurrent convolutional network (LRCN) is adopted to realize vocal detection, and the results confirm that the proposed singing voice detection algorithm reached the state-of-the-art level on public datasets.
- Video-Based Person Re-Identification via Self Paced Weighting31
A novel video-based person re-id method via self paced weighting (SPW) is proposed, which proposes a self paced outlier detection method to evaluate the noise degree of video sub sequences and a weighted multi-pair distance metric learning approach is adopted to measure the distance of two person image sequences.
- Ensemble Super-Resolution With a Reference Dataset30
This paper presents a simple but effective single image SR method based on ensemble learning, which can produce a better performance than that could be obtained from any of SR methods to be ensembled (or called component super-resolvers).
- 27
- HarmoF0: Logarithmic Scale Dilated Convolution for Pitch Estimation26
This paper introduces a multiple rates dilated causal convolution method to capture the harmonic structure in logarithmic scale spectrograms efficiently and proposes HarmoF0, a fully convolutional network to evaluate the MRDC-Conv and other dilated convolutions in pitch estimation.
- Emotionally Enhanced Talking Face Generation25
This work builds a talking face generation framework conditioned on a categorical emotion to generate videos with appropriate expressions, making them more realistic and convincing.
- Multi-Level Fusion for Person Re-identification with Incomplete Marks25
This paper studies the problem of Person Re-identification with Incomplete Marks (PRIM), aiming at ranking the persons in the gallery according to both the videos and incomplete marks, and shows that through introducing marks, the retrieval accuracy is significantly improved.
- Combining multi-probe histogram and order-statistics based LSH for scalable audio content retrieval25
A new multi-stage LSH scheme that consists in extracting compact but accurate representations from audio tracks by exploiting the LSH idea to summarize audio tracks and adequately organizing the resulting representations in LSH tables, retaining almost the same accuracy as an exact kNN retrieval is suggested.
- Variational Autoencoder with CCA for Audio–Visual Cross-modal Retrieval24
A novel variational autoencoder architecture is presented that is effective in learning audio–visual correlation and is appreciably better than the existing cross-modal retrieval methods.
- 24
- User preference-aware music video generation based on modeling scene moods24
A music video generation/creation system that aims to make UGVs more attractive by generating scene-adaptive and user-preference aware music tracks and can effectively combine objective scene moods and individual music tastes to recommend appealing soundtracks for videos.
- Conditional hybrid GAN for melody generation from lyrics22
A novel conditional hybrid GAN (C-Hybrid-GAN) for melody generation from lyrics is proposed, which contains three independent branches (each for one melody attribute) in the generator and one branch for distinguishing concatenated attributes in the discriminator.
- 22
- 22
- Singer Identification Using Deep Timbre Feature Learning with KNN-NET21
The proposed KNN-Net for SID is a deep neural network model with the goal of learning local timbre feature representation from the mixture of singer voice and background music, which outperforms the state-of-the-art methods.
- Multi-scale patch based representation feature learning for low-resolution face recognition20
The proposed MSPRFL approach first exploits multi-level information to learn more accurate resolution-robust representation features of each patch with the help of a training dataset, and tries to fuse the multi-scale outputs by learning scale weights via an ensemble optimization model.
- Correlation Discrepancy Insight Network for Video Re-identification20
A novel correlation discrepancy insight network for video-based person ReID is proposed, which consists of an unsupervised correlation insight model for video purification and a discrepancy description network (DDN) for person representation that outperforms several state-of-the-art methods.
- 19
- Concept-Level Multimodal Ranking of Flickr Photo Tags via Recall Based Weighting18
This work proposes a tag ranking scheme based on voting from photo neighbors derived from multimodal information that determines photo neighbors leveraging geo, visual, and semantics concepts derived from spatial information, visual content, and textual metadata, respectively.
- NEWSMAN: Uploading Videos over Adaptive Middleboxes to News Servers in Weak Network Infrastructures18
This study introduces an adaptive middlebox design, called NEWSMAN, to support citizen journalists, and designs, implements, and evaluates an efficient scheduling algorithm to maximize a user-specified objective function.
- Local summarization and multi-level LSH for retrieving multi-variant audio tracks18
Experimental evaluations performed on a real multi-variant audio dataset confirm that the approach relying on local summarization and multi-level Locality-Sensitive Hashing supports fast and reliable retrieval of audio track variants.
- Learning Explicit and Implicit Dual Common Subspaces for Audio-visual Cross-modal Retrieval17
A novel end-to-end architecture is proposed, which synchronously projects audio-visual data into the explicit and the implicit dual common subspaces to solve the modality gap and significantly outperforms the state-of-the-art cross-modal models that learn features from a single common subspace.
- Lyrics-Conditioned Neural Melody Generation16
By exploiting a large music dataset with 12,197 pairs of English lyrics and melodies, a lyrics-conditioned AI neural melody generation system that consists of three components: lyrics encoder network, melody generation network, and MIDI sequence tuner is developed.
- Using Psychoacoustic Models for Sound Analysis in Music15
It is observed that roughness is the most crucial sound resemblance criteria, followed by sharpness, loudness, spaciousness and tonalness, which indicates that these psychoacoustic models may be suitable for music data mining, music browsing, automatic playlist generation and music recommendation tasks.
- Predicting User Preference Based on Matrix Factorization by Exploiting Music Attributes14
This work proposes to predict the users' preferred music feature's value by modeling, not only usage information, but also music description features by treating music feature values as virtual users and retrieves the preferred feature values for real target users.
- Statistical Inference of Gaussian-Laplace Distribution for Person Verification13
Experiments conducted on a metric learning method by exploiting Gaussian-Laplace distribution statistical inference show its superiority in terms of effectiveness and efficiency as compared with the state-of-the-art approaches, no matter the appearance description is handcrafted or deep learned.
- 13
- Social interactions over geographic-aware multimedia systems13
This tutorial delivers a better understanding of the basics of location-aware contextual descriptions and its relations to social multimedia scenes, and may also serve to highlight relationships that can be collaboratively applied to multimodal retrieval and recommendation technology.
- Edge-based locality sensitive hashing for efficient geo-fencing application13
An efficient algorithm to improve the scalability of geo-fencing is proposed, which consists of two main stages and can achieve a fast speed while retaining 100% accuracy over all training datasets provided by the GIS Cup 2013 organizers.
- 12
- Beyond Learned Metadata-Based Raw Image Reconstruction12
A novel framework that learns a compact representation in the latent space, serving as metadata, in an end-to-end manner is proposed, achieving high-quality raw image reconstruction with a smaller metadata size, compared with existing SOTA methods.
- 12
- Query-Guided Prototype Learning with Decoder Alignment and Dynamic Fusion in Few-Shot Segmentation12
A query-guided prototype learning architecture to address the problem of inaccurate predictions when directly compared with features extracted from the query set, and proposes a cross-alignment loss for training the segmentation decoder.
- Image super-resolution via multi-view information fusion networks12
A lightweight network structure for super-resolution which adopts the multi-view information fusion strategy and a global-relation attention block to enable interactions among groups and an enhancement block to better extract and fuse multi-scale feature information is proposed.
- Deep Learning of Human Perception in Audio Event Classification12
The experimental results demonstrate that i) audio event classification can be improved by exploiting the power of human perception, and ii) the correlation between audio stimuli and EEG can be learned to complement audio event understanding.
- 12
- MULTI-VERSION MUSIC SEARCH USING ACOUSTIC FEATURE UNION AND EXACT SOFT MAPPING12
This work proposes audio-based music indexing techniques, ELSM and Soft Locality Sensitive Hash (SoftLSH) using an optimized Feature Union (FU) set of extracted audio features and proves that the algorithms are effective for both multi-version detection and same content detection.
- Indexing high-dimensional data in dual distance spaces: a symmetrical encoding approach12
The results demonstrate that this method outperforms the state-of-the-art high dimensional search techniques such as the X-Tree, VA-file, iDistance and NB- tree, especially when the query radius is not very large.
- Melody Generation from Lyrics with Local Interpretability11
A model for melody generation from lyrics with local interpretability is proposed, which contains two significant contributions: Mutual information between input lyrics and generated melody is exploited to instruct the training of the network, which avoids the loss of content consistency during the training stage.
- Graph-Based Video-Language Learning with Multi-Grained Audio-Visual Alignment9
This work proposes a multi-grained alignment module that aligns the audio and visual features at multiple scales to effectively fuse theaudio and visual information in a way that is consistent with the semantic-level information captured by the graph-based representations.
- 9
- 9
- 9
- 8
- 8
- 8
- Deep Multi-label Hashing for Large-Scale Visual Search Based on Semantic Graph8
Extensive experiments over several large image datasets confirm that the proposed DMLH method outperforms state-of-the-art supervised and unsupervised image retrieval approaches, with a gain ranging from 6.25% to 38.9% in terms of mean average precision.
- 8
- 7
- 7
- Enhancing semantic audio-visual representation learning with supervised multi-scale attention6
This paper proposes a novel supervised multi-scale attention for enhancing semantic audio-visual representation learning from multimedia data, utilizing the audio-visual attention mechanism to combine multi-scale features.
- 6
- 6
- 6
- 6
- 6
- Face hallucination through differential evolution parameter map learning with facial structure prior6
Experimental results demonstrate that results of proposed parameter map learning method are comparable to or better than those traditional unified parameter setting methods and some recently proposed deep learning methods.
- 6
- 5
- 5
- 5
- 5
- 5
- SIST: Online Scale-Adaptive Object tracking with Stepwise Insight5
This work proposes an online scale-adaptive correlation tracker by collaboratively learning a target-insight model (TIM) for object localization and a scale-insights model (SIM) for progressive refinement, which outperforms several state-of-the-art methods.
- 5
- 5
- 4
- Robust Facial Image Super-Resolution by Kernel Locality-Constrained Coupled-Layer Regression4
This research presents a new super-resolution method for facial image via representation learning scheme that addresses the key problem for the super- resolution of facial image: high-resolution face recognition.
- 4
- 4
- 4
- 4
- 4
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- 2
- 2
- 2
- 2
- Adaptive Margin Nearest Neighbor for Person Re-Identification2
An Adaptive Margin Nearest Neighbor (AMNN) method is proposed, which aims to take unequal treatment to each samples impostors by pushing them to adaptive variable margins away, and is confirmed the superiority of the proposed method.
- 2
- 2
- 2
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-16. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it.