Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileAcademic lineage
Possible advisorsa guess from early papers, not confirmed
- Nicu SebeSuggested from co-authorship
- Yangsheng XuSuggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works172 from public data
- PAD-Net: Multi-tasks Guided Prediction-and-Distillation Network for Simultaneous Depth Estimation and Scene Parsing582
This paper proposes a novel multi-task guided prediction-and-distillation network (PAD-Net), which first predicts a set of intermediate auxiliary tasks ranging from low level to high level, and then the predictions from these intermediate Auxiliary tasks are utilized as multi-modal input via the authors' proposed multi- modal distillation modules for the final tasks.
- GS-SLAM: Dense Visual SLAM with 3D Gaussian Splatting571
GS-SLAM is introduced that first utilizes 3D Gaussian representation in the Simultaneous Localization and Mapping (SLAM) system and proposes an adaptive expansion strategy that adds new or deletes noisy 3D Gaussians in order to efficiently reconstruct new observed scene geometry and improve the mapping of pre-viously observed areas.
- Learning Deep Representations of Appearance and Motion for Anomalous Event Detection550
This work proposes Appearance and Motion DeepNet (AMDN) which utilizes deep neural networks to automatically learn feature representations, and introduces a novel double fusion framework, combining both the benefits of traditional early fusion and late fusion strategies.
- Detecting anomalous events in videos by learning deep representations of appearance and motion474
A novel double fusion framework is introduced, combining the benefits of traditional early fusion and late fusion strategies, which is extensively evaluated on publicly available video surveillance datasets including UCSD pedestian, Subway, and Train, showing competitive performance with respect to state of the art approaches.
- Multi-scale Continuous CRFs as Sequential Deep Networks for Monocular Depth Estimation466
This paper addresses the problem of depth estimation from a single still image by designing a novel CNN implementation of mean-field updates for continuous CRFs and demonstrates the effectiveness of the proposed approach and establishes new state of the art results on publicly available datasets.
- Structured Attention Guided Convolutional Neural Fields for Monocular Depth Estimation348
This paper introduces a novel approach for monocular depth estimation which is competitive with previous methods on the KITTI benchmark and outperforms the state of the art on the NYU Depth V2 dataset.
- Multi-class Token Transformer for Weakly Supervised Semantic Segmentation321
A Multi-class Token Transformer, termed as MCTformer, which uses multiple class tokens to learn interactions between the class tokens and the patch tokens, which can successfully produce class-discriminative object localization maps from the class-to-patch attentions corresponding to different class tokens.
- Delving into Localization Errors for Monocular 3D Object Detection309
This work quantifies the impact introduced by each sub-task and found the ‘localization error’ is the vital factor in restricting monocular 3D detection, and investigates the underlying reasons behind localization errors.
- AttentionGAN: Unpaired Image-to-Image Translation Using Attention-Guided Generative Adversarial Networks292
A new Attention-Guided Generative Adversarial Networks (AttentionGAN) is proposed for the unpaired image-to-image translation task which can identify the most discriminative semantic objects and minimize changes of unwanted parts for semantic manipulation problems without using extra data and models.
- Depth-Aware Generative Adversarial Network for Talking Head Video Generation260
A self-supervised face-depth learning method to automatically recover dense 3D facial geometry (i.e. depth) from the face videos without the requirement of any expensive 3D annotation data is introduced.
- 245
- Multi-Channel Attention Selection GAN With Cascaded Semantic Guidance for Cross-View Image Translation239
A novel approach named Multi-Channel Attention SelectionGAN (SelectionGAN) that makes it possible to generate images of natural scenes in arbitrary viewpoints, based on an image of the scene and a novel semantic map, using a multi-channel attention selection mechanism.
- Learning Cross-Modal Deep Representations for Robust Pedestrian Detection237
The proposed approach outperforms the state-of-the-art on the challenging KAIST multispectral pedestrian dataset and it is competitive with previous methods on the popular Caltech dataset.
- Unsupervised Adversarial Depth Estimation Using Cycled Generative Networks193
A novel unsupervised deep learning approach for predicting depth maps and showing that the depth estimation task can be effectively tackled within an adversarial learning framework is presented.
- Leveraging Auxiliary Tasks with Affinity Learning for Weakly Supervised Semantic Segmentation175
This work proposes a novel weakly supervised multi-task framework termed as AuxSegNet, to leverage saliency detection and multi-label image classification as auxiliary tasks to improve the primary task of semantic segmentation using only image-level ground-truth labels.
- Local Class-Specific and Global Image-Level Generative Adversarial Networks for Semantic-Guided Scene Generation161
This work considers learning the scene generation in a local context, and correspondingly design a local class-specific generative network with semantic maps as a guidance, which separately constructs and learns sub-generators concentrating on the generation of different classes and is able to provide more scene details.
- Dynamic Graph Message Passing Networks157
A dynamic graph message passing network, that significantly reduces the computational complexity compared to related works modelling a fully-connected graph by adaptively sampling nodes in the graph, conditioned on the input, for message passing.
- Attention-Guided Generative Adversarial Networks for Unsupervised Image-to-Image Translation151
This paper proposes a novel Attention-Guided Generative Adversarial Network (AGGAN), which can detect the most discriminative semantic object and minimize changes of unwanted part for semantic manipulation problems without using extra data and models.
- DetCLIPv2: Scalable Open-Vocabulary Object Detection Pre-training via Word-Region Alignment137
An efficient and scalable training framework that incorporates large-scale imagetext pairs to achieve open-vocabulary object detection (OVD) and is trained with a hybrid supervision from detection, grounding and image-text pair data under a unified data formulation.
- Learning Deep Structured Multi-Scale Features using Attention-Gated CRFs for Contour Prediction134
A hierarchical deep model is introduced which produces more rich and complementary representations and the novel Attention-Gated Conditional Random Fields (AG-CRFs) are proposed to refine and robustly fuse the representations learned at different scales.
- Cross-modal Consensus Network for Weakly Supervised Temporal Action Localization115
This work argues that the features extracted from the pre-trained extractors are not specific for WS-TAL task, leading to inevitable redundancy and sub-optimization, and proposes a cross-modal consensus network (CO2-Net) to tackle this problem.
- Monocular Depth Estimation Using Multi-Scale Continuous CRFs as Sequential Deep Networks112
This paper addresses the problem of monocular depth estimation from a single still image by designing a novel CNN implementation of mean-field updates for continuous CRFs and proposes two different variations, one based on a cascade of multiple CRFs, the other on a unified graphical model.
- Video anomaly detection based on a hierarchical activity discovery within spatio-temporal contexts107
A novel approach for video-anomaly detection in crowded and complicated scenes based on a hierarchical activity-pattern discovery framework, comprehensively considering both global and local spatio-temporal contexts is presented.
- Uncertainty-Aware Contrastive Distillation for Incremental Semantic Segmentation106
A novel distillation framework, Uncertainty-aware Contrastive Distillation, that takes into account all the images in a mini-batch, enforcing similarity between features associated to all the pixels from the same classes, and pulling apart those corresponding to pixels from different classes is proposed.
- GestureGAN for Hand Gesture-to-Gesture Translation in the Wild99
Extensive experiments demonstrate that the proposed GestureGAN achieves state-of-the-art performance on the unconstrained hand gesture-to-gesture translation task and the generated images are in high-quality and are photo-realistic, allowing them to be used as data augmentation to improve the performance of a hand gesture classifier.
- Generalized Binary Search Network for Highly-Efficient Multi-View Stereo92
A novel method for highly efficient MVS that remarkably decreases the memory footprint, meanwhile clearly advancing state-of-the-art depth prediction performance and greatly facilitates quick training convergence is proposed.
- Cycle In Cycle Generative Adversarial Networks for Keypoint-Guided Image Generation87
The proposed C2GAN is a cross-modal framework exploring a joint exploitation of the keypoint and the image data in an interactive manner, which provides complementary information from the two different modalities and brings extra supervision across cycles, thus facilitating more robust optimization of the whole network.
- SA-ConvONet: Sign-Agnostic Optimization of Convolutional Occupancy Networks86
This work proposes to learn implicit surface reconstruction by sign-agnostic optimization of convolutional occupancy networks, to simultaneously achieve advanced scalability to large-scale scenes, generality to novel shapes, and applicability to raw scans in a unified framework.
- Implicit Identity Representation Conditioned Memory Compensation Network for Talking Head Video Generation84
This work designs a novel implicit identity representation conditioned memory compensation network, coined as MCNet, that can learn representative and complementary facial memory, and can clearly outperform previous state-of-the-art talking head generation methods on VoxCeleb1 and CelebV datasets.
- Online Dynamic Gesture Recognition for Human Robot Interaction79
An online dynamic hand gesture recognition system with an RGB-D camera, which can automatically recognize hand gestures against complicated background, and develops a human-robot interactive system that demonstrates the effectiveness of the proposed system.
- MCTformer+: Multi-Class Token Transformer for Weakly Supervised Semantic Segmentation78
A novel transformer-based framework to generate accurate class-specific object localization maps for weakly supervised semantic segmentation (WSSS) and introduces a Contrastive-Class-Token (CCT) module to enhance the learning of discriminative class tokens, enabling the model to better capture the unique characteristics of each class.
- TaskExpert: Dynamically Assembling Multi-Task Representations with Memorial Mixture-of-Experts76
The proposed TaskExpert is a novel multi-task mixture-of-experts model that enables learning multiple representative task-generic feature spaces and decoding task-specific features in a dynamic manner and clearly outperforms previous best-performing methods on all 9 metrics of two competitive multi-task learning benchmarks for visual scene understanding.
- 76
- Spatio-temporal context analysis within video volumes for anomalous-event detection and localization76
This approach is an unsupervised statistical learning framework based on analysis of spatio-temporal video-volume configuration within video cubes that not only detects various anomalies more efficiently, but also locates anomalous regions more accurately.
- DetCLIPv3: Towards Versatile Generative Open-Vocabulary Object Detection74
In this pa-per, DetCLIPv3 is introduced, a high-performing detector that excels not only at both open-vocabulary object detection, but also generating hierarchical labels for detected objects.
- Every Smile is Unique: Landmark-Guided Diverse Smile Generation71
This work proposes a novel deep learning architecture named Conditional Multi-Mode Network (CMM-Net), which explicitly exploits facial landmarks for generating smile sequences and demonstrates the effectiveness of this architecture in generating realistic videos of multiple smile expressions.
- MotionGPT-2: A General-Purpose Motion-Language Model for Motion Generation and Understanding70
The proposed MotionGPT-2 is highly adaptable to the challenging 3D holistic motion generation task, enabled by the innovative motion discretization framework, Part-Aware VQVAE, which facilitates fine-grained representations of body and hand movements.
- Structured Modeling of Joint Deep Feature and Prediction Refinement for Salient Object Detection56
This paper designs a novel cascade CRFs architecture with CNN to jointly refine deep features and predictions at each scale and progressively compute a final refined saliency map, and formulate the CRF graphical model that involves message-passing of feature-feature, feature-prediction, and prediction-predicted, from the coarse scale to the finer scale.
- X-VILA: Cross-Modality Alignment for Large Language Model50
This work introduces X-VILA, an omni-modality model designed to extend the capabilities of large language models (LLMs) by incorporating image, video, and audio modalities, and proposes a visual alignment mechanism with a visual embedding highway module that exhibits proficiency in any-to-any modality conversation.
- Dual Generator Generative Adversarial Networks for Multi-domain Image-to-Image Translation46
A Dual Generator Generative Adversarial Network (G$^2$GAN) is proposed, which is a robust and scalable approach allowing to perform unpaired image-to-image translation for multiple domains using only dual generators within a single model.
- Learning Parallel Dense Correspondence from Spatio-Temporal Descriptors for Efficient and Robust 4D Reconstruction45
This work presents a novel pipeline to learn a temporal evolution of the 3D human shape through spatially continuous transformation functions among cross-frame occupancy fields via explicitly learning continuous displacement vector fields from robust spatio-temporal shape representations.
- Continual Attentive Fusion for Incremental Learning in Semantic Segmentation44
A novel attentive feature distillation approach to mitigate catastrophic forgetting while accounting for semantic spatial- and channel-level dependencies is introduced and a continual attentive fusion structure is proposed, which takes advantage of the attention learned from the new and the old tasks while learning features for the new task.
- 44
- InvPT++: Inverted Pyramid Multi-Task Transformer for Visual Scene Understanding39
This work proposes an Inverted Pyramid multi-task Transformer, capable of modeling cross-task interaction among spatial features of different tasks in a global context, and two types of Cross-Scale Self-Attention modules are proposed to efficiently facilitate cross-task interaction across different feature scales.
- DaGAN++: Depth-Aware Generative Adversarial Network for Talking Head Video Generation38
A novel self-supervised method for learning dense 3D facial geometry (i.e., depth) from face videos, without requiring camera parameters and 3D geometry annotations in training is presented, and a strategy to learn pixel-level uncertainties to perceive more reliable rigid-motion pixels for geometry learning is proposed.
- 38
- Anomaly Detection in Video Surveillance via Gaussian Process36
A new approach for anomaly detection in video surveillance is proposed based on a nonparametric Bayesian regression model built upon Gaussian process priors.
- Taming Video Diffusion Prior with Scene-Grounding Guidance for 3D Gaussian Splatting from Sparse Inputs35
This work introduces a novel scene-grounding guidance based on rendered sequences from an optimized 3DGS, which tames the diffusion model to generate consistent sequences and proposes a trajectory initialization method that effectively identifies regions that are outside the field of view and occluded.
- Text-to-3D Generation with Bidirectional Diffusion Using Both 2D and 3D Priors33
Bidirectional Diffusion is proposed, a unified framework that incorporates both a 3D and a 2D diffusion process to preserve both 3D fidelity and 2D texture richness, respectively, and can be used as an initialization of optimization-based models to further improve the quality of 3D models and the efficiency of optimization.
- Progressive Fusion for Unsupervised Binocular Depth Estimation Using Cycled Networks32
This paper introduces a new network architecture, named Progressive Fusion Network (PFN), that is specifically designed for binocular stereo depth estimation, based on a multi-scale refinement strategy that combines the information provided by both stereo views.
- 31
- 31
- Edge Guided GANs with Semantic Preserving for Semantic Image Synthesis30
A novel Edge guided Generative Adversarial Network (EdgeGAN) for photo-realistic image synthesis from semantic layouts that can generate significantly better results than state-of-the-art methods.
- 29
- From One to More: Contextual Part Latents for 3D Generation28
A new part-based 3D generation framework, CoPart, which represents a 3D object with multiple contextual part latents and simultaneously generates coherent 3D parts and proposes a novel mutual guidance strategy to fine-tune pre-trained diffusion models for joint part latent denoising.
- Implicit Event-RGBD Neural SLAM28
EN-SLAM is proposed, the first event-RGBD implicit neural SLAM framework, which effectively leverages the high rate and high dynamic range advantages of event data for tracking and mapping and outperforms the SOTA methods in both tracking ATE and mapping ACC with a real-time 17 FPS in various challenging environments.
- Probabilistic Graph Attention Network with Conditional Kernels for Pixel-Wise Prediction28
Quantitative and qualitative results demonstrate the effectiveness of the proposed latent AG-CRF model and the overall probabilistic graph attention network with feature conditional kernels for structured feature learning and pixel-wise prediction.
- MM-Ego: Towards Building Egocentric Multimodal LLMs for Video QA27
MM-Ego is built, an egocentric multimodal LLM that shows powerful performance on egocentric video understanding and includes a specialized multimodal architecture featuring a novel"Memory Pointer Prompting"mechanism that enables the model to more effectively comprehend extended video content.
- DiffusionMTL: Learning Multi-Task Denoising Diffusion Model from Partially Annotated Data27
Extensive quantitative and qualitative experiments demonstrate that the proposed multi-task denoising diffusion model can significantly improve multi-task prediction maps, and out-perform the state-of-the-art methods on three challenging multi-task benchmarks, under two different partial-labeling evaluation settings.
- Learning How to Smile: Expression Video Generation With Conditional Adversarial Recurrent Nets26
A novel deep generative model able to produce face videos from a given image of a neutral face and a label indicating a specific facial expression, e.g. spontaneous smile is proposed.
- 25
- Interactive3D: Create What You Want by Interactive 3D Generation24
This work introduces Interactive3D, an innovative framework for interactive 3D generation that grants users precise control over the generative process through extensive 3D interaction capabilities and markedly improves the controllability and quality of 3D generation.
- Expression Conditional Gan for Facial Expression-to-Expression Translation24
A novel Expression Conditional GAN which can learn the mapping from one image domain to another one based on an additional expression attribute and is applicable to different expression generation tasks where specific facial expression can be easily controlled by the conditional attribute label.
- Attribute-Guided Sketch Generation24
A novel Attribute-Guided Sketch Generative Adversarial Network (ASGAN) which is an end-to-end framework and contains two pairs of generators and discriminators that generates more photo-realistic faces with sharper facial attributes than baselines and has good generalization capability on different generative tasks.
- 23
- Cross-Paced Representation Learning With Partial Curricula for Sketch-Based Image Retrieval23
The cross-paced partial curriculum learning (CPPCL) framework is introduced, specifically designed to assess the learning pace by jointly handling data from dual sources and modality-specific prior information provided in the form of partial curricula.
- 22
- Structured Coupled Generative Adversarial Networks for Unsupervised Monocular Depth Estimation22
A new end-to-end unsupervised deep learning framework for monocular depth estimation consisting of two Generative Adversarial Networks (GAN), deeply coupled with a structured Conditional Random Field (CRF) model to fuse the generative and discriminative outputs from the dual GAN nets.
- Viraliency: Pooling Local Virality22
This work introduces a pooling layer that learns the size of the support area to be averaged: the learned top-N average (LENA) pooling, and assesses the effectiveness of the LENA layer by appending it on top of a convolutional siamese architecture and evaluates its performance on the task of predicting and localizing virality.
- 21
- Learning Unified Decompositional and Compositional NeRF for Editable Novel View Synthesis20
A unified Neural Radiance Field (NeRF) framework to effectively perform joint scene decomposition and composition for modeling real-world scenes, outperforming state-of-the-art methods for both novel-view synthesis and editing tasks.
- Collaborative Novel Object Discovery and Box-Guided Cross-Modal Alignment for Open-Vocabulary 3D Object Detection19
A unified framework designed to innovatively tackle both the localization and classification of novel 3D objects, under the condition of limited base categories is proposed, demonstrating the superiority of CoDAv2.
- 18
- 18
- Moving SLAM: Fully Unsupervised Deep Learning in Non-Rigid Scenes17
A new deep learning framework to decompose monocular videos into 3D geometry (camera pose and depth), moving objects, and their motions, with no supervision, with very competitive results on unsupervised odometry and depth prediction on KITTI.
- CVT-xRF: Contrastive In-Voxel Transformer for 3D Consistent Radiance Fields from Sparse Inputs16
A novel approach that models 3D spatial field consistency to improve NeRF's performance with sparse inputs by adopting a voxel-based ray sampling strategy and using a contrastive loss on the encoder output of the Transformer to further improve consistency within each voxel is proposed.
- Reducing Spatial Labeling Redundancy for Active Semi-Supervised Crowd Counting16
This work proposes to break the labeling chain of previous methods and make the first attempt to reduce spatial labeling redundancy for semi-supervised crowd counting, and identifies the region representativeness from both vertical and horizontal directions of initially estimated density maps, and formulate them as cluster centers of Gaussian Mixture Models.
- Auxiliary Tasks Enhanced Dual-Affinity Learning for Weakly Supervised Semantic Segmentation15
A cross-task dual-affinity learning module to learn both pairwise and unary affinities, which are used to enhance the task-specific features and predictions by aggregating both query-dependent and query-independent global context for both saliency detection and semantic segmentation.
- Contrastive Multi-Task Dense Prediction15
A novel multi-task contrastive regularization method based on the consistency to effectively boost the representation learning of the different sub-tasks, which can also be easily generalized to different multi- task dense prediction frameworks, and costs no additional computation in the inference.
- Fine-grained Domain Adaptive Crowd Counting via Point-derived Segmentation14
This work proposes to untangle domain-invariant crowd and domain-specific background from crowd images and design a fine-grained domain adaption method for crowd counting, which outperforms previous approaches consistently in the widely-used adaptation scenarios.
- Deep Micro-Dictionary Learning and Coding Network14
The proposed DDLCN achieves competitive results compared with state-of-the-art approaches and is empirically compare with several dictionary learning methods and deep learning architectures.
- Searching Action Proposals via Spatial Actionness Estimation and Temporal Path Inference and Tracking14
The proposed approach starts from actionness estimation on frame-level bounding boxes, and then aggregates the bounded boxes belonging to the same actor across frames via linking, associating, tracking to generate spatial-temporal continuous action paths.
- Academic Coupled Dictionary Learning for Sketch-based Image Retrieval14
This work introduces academic learning, a paradigm in which the sample learning order is constructed both from the data, as in self-paced learning, and from partial curricula, and proposes an instantiation of this paradigm within the framework of coupled dictionary learning to address the SBIR task.
- Holistic-Motion2D: Scalable Whole-body Human Motion Generation in 2D Space13
This paper presents Holistic-Motion2D, the first comprehensive and large-scale benchmark for 2D whole-body motion generation, which includes over 1M in-the-wild motion sequences, each paired with high-quality whole-body/partial pose annotations and textual descriptions.
- 13
- 12
- 12
- An adaptive and scalable artificial neural network-based model-order-reduction method for large-scale topology optimization designs11
An adaptive, scalable deep learning-based model-order-reduction method is proposed to accelerate large-scale TO process, by utilizing MapNet, a neural network which maps the field of interest from coarse-scale to fine-scale.
- 9
- 8
- 7
- 6
- VGGT-Det: Mining VGGT Internal Priors for Sensor-Geometry-Free Multi-View Indoor 3D Object Detection6
VGGT-Det is presented, the first framework tailored for SG-Free multi-view indoor 3D object detection, which integrates VGGT encoder into a transformer-based pipeline and introduces two novel key components: Attention-Guided Query Generation and Query-Driven Feature Aggregation.
- 6
- Variational Structured Attention Networks for Deep Visual Representation Learning6
VISTA-Net outperforms the state-of-the-art in multiple continuous and discrete prediction tasks, thus confirming the benefit of the proposed approach in joint structured spatial-channel attention estimation for deep representation learning.
- 6
- 5
- 5
- 5
- 4
- 4
- 4
- UniMC: Taming Diffusion Transformer for Unified Keypoint-Guided Multi-Class Image Generation3
A DiT-based framework, named UniMC, is designed to explore unifying controllable multi-class image generation, and a large-scale, high-quality, and diverse dataset designed for keypoint-guided human and animal image generation is proposed.
- 3
- 3
- 3
- 3
- 3
- 2
- 2
- Learning class-agnostic masks with cross-task refinement for weakly supervised semantic segmentation2
This work proposes to jointly learn semantic segmentation and class-agnostic masks by using image-level annotations and off-the-shelf saliency maps as supervision, and introduces a new normalization method for CAM to generate more complete class-specific localization maps.
- 2
- Multimedia Content Understanding in Harsh Environments2
This tutorial introduces some multimedia enhancement methods, presents recent advances in 2D and 3D visual scene understanding, shows strategies to estimate the prediction uncertainty, provides a brief summary, and shows some typical applications.
- 2
- 2
- 2
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- –
- –
- –
- –
- –
- –
- –
- –
- AsySplat: Efficient Asymmetric 3D Gaussian Splatting for Long-Sequence Scene Modeling–
This model matches optimization-based methods while delivering nearly 800x speedup, and surpasses the zero-shot performance of state-of-the-art generalizable models with markedly fewer parameters and reduced training/inference overhead, achieving an overall efficiency improvement.
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- UoLMM'22: 2nd International Workshop on Robust Understanding of Low-quality Multimedia Data: Unitive Enhancement, Analysis and Evaluation–
The purpose of this workshop is to bring together individuals in three areas: enhancement, analysis, and evaluation, for sharing ideas and discussion on current developments and future directions.
- –
- –
- –
- –
- –
- –
- –
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.