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
- Suggested from co-authorship
- Ling ShaoSuggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works190 from public data
- Salient Object Detection in the Deep Learning Era: An In-Depth Survey810
This paper reviews deep SOD algorithms from different perspectives, including network architecture, level of supervision, learning paradigm, and object-/instance-level detection, and looks into the generalization and difficulty of existing SOD datasets.
- Video Salient Object Detection via Fully Convolutional Networks642
A novel data augmentation technique that simulates video training data from existing annotated image data sets, which enables the deep video saliency network to learn diverse saliency information and prevents overfitting with the limited number of training videos.
- Exploring Cross-Image Pixel Contrast for Semantic Segmentation596
This work raises a pixel-wise metric learning paradigm for semantic segmentation, by explicitly exploring the structures of labeled pixels, which were rarely explored before, and hopes this work will encourage the community to rethink the current de facto training paradigm in semantic segmentsation.
- Learning Human-Object Interactions by Graph Parsing Neural Networks596
This paper addresses the task of detecting and recognizing human-object interactions (HOI) in images and videos with the Graph Parsing Neural Network (GPNN), a framework that incorporates structural knowledge while being differentiable end-to-end.
- Poly Kernel Inception Network for Remote Sensing Detection544
The Poly Kernel Inception Network (PKINet) is introduced, which employs multi-scale convolution kernels without dilation to extract object features of varying scales and capture local context in remote sensing images.
- 543
- See More, Know More: Unsupervised Video Object Segmentation With Co-Attention Siamese Networks537
This work introduces a novel network, called as CO-attention Siamese Network (COSNet), to address the unsupervised video object segmentation task from a holistic view and proposes a unified and end-to-end trainable framework where different co-att attention variants can be derived for mining the rich context within videos.
- 535
- 510
- Pyramid Dilated Deeper ConvLSTM for Video Salient Object Detection492
This paper proposes a fast video salient object detection model, based on a novel recurrent network architecture, named Pyramid Dilated Bidirectional ConvLSTM (PDB-ConvL STM), which achieves state-of-the-art results on two popular benchmarks, well demonstrating its superior performance and high applicability.
- 472
- Human-Aware Motion Deblurring403
A human-aware deblurring model that disentangles the motion blur between foreground (FG) humans and background (BG) humans based on a triple-branch encoder-decoder architecture that performs favorably against the state-of-the-art motion deblurred methods, especially in capturing semantic details.
- 395
- Learning Pose Grammar to Encode Human Body Configuration for 3D Pose Estimation392
This paper proposes a pose grammar to tackle the problem of 3D human pose estimation, which takes 2D pose as input and learns a generalized 2D-3D mapping function and enforces high-level constraints over human poses.
- 384
- A Survey on 3D Gaussian Splatting383
The first systematic overview of the recent developments and critical contributions in 3D GS is provided, with a detailed exploration of the underlying principles and the driving forces behind the emergence of 3D GS, laying the groundwork for understanding its significance.
- Rethinking Semantic Segmentation: A Prototype View377
This study uncovers several limitations of such parametric segmentation regime, and proposes a nonparametric alternative based on non-learnable prototypes, which allows the model to directly shape the pixel embedding space, by optimizing the arrangement between embedded pixels and anchored prototypes.
- Mining Cross-Image Semantics for Weakly Supervised Semantic Segmentation359
This paper addresses the value of cross-image semantic relations for comprehensive object pattern mining and provides a unified framework that handles well different WSSS settings, i.e., learning WSSD with (1) precise image-level supervision only, (2) extra simple single-label data, and (3) extra noisy web data.
- 348
- 342
- 329
- A Survey on Deep Learning Technique for Video Segmentation316
This survey comprehensively review two basic lines of research — generic object segmentation in videos, and video semantic segmentation — by introducing their respective task settings, background concepts, perceived need, development history, and main challenges.
- Revisiting Video Saliency: A Large-Scale Benchmark and a New Model311
This work introduces a new benchmark for predicting human eye movements during dynamic scene free-viewing, and proposes a novel video saliency model that augments the CNN-LSTM network architecture with an attention mechanism to enable fast, end-to-end saliency learning.
- Video Object Segmentation with Episodic Graph Memory Networks303
This work exploits an episodic memory network, organized as a fully connected graph, to store frames as nodes and capture cross-frame correlations by edges and yields a neat yet principled framework, which can generalize well both one-shot and zero-shot video object segmentation tasks.
- Zero-Shot Video Object Segmentation via Attentive Graph Neural Networks302
This work proposes a novel attentive graph neural network (AGNN) for zero-shot video object segmentation (ZVOS) and extends it to an additional task: image object co-segmentation (IOCS), demonstrating the generalizability of the framework.
- 296
- ETPNav: Evolving Topological Planning for Vision-Language Navigation in Continuous Environments292
A new navigation framework, ETPNav, which focuses on two critical skills: the capability to abstract environments and generate long-range navigation plans, and the ability of obstacle-avoiding control in continuous environments.
- Segment and Track Anything283
SAM-Track amalgamates Segment Anything Model (SAM), an interactive key-frame segmentation model, with the proposed AOT-based tracking model (DeAOT), which secured 1st place in four tracks of the VOT 2022 challenge, to facilitate object tracking in video.
- 242
- 241
- 236
- 234
- 218
- Visual Recognition with Deep Nearest Centroids217
DNC is devised, a conceptually elegant yet surprisingly effective network for large-scale visual recognition, by revisiting Nearest Centroids, one of the most classic and simple classifiers, and brings fundamental insights into related fields.
- 216
- 205
- Deep Hierarchical Semantic Segmentation198
HSSN is devised, a general HSS framework that tackles two critical issues in this task: how to efficiently adapt existing hierarchy-agnostic segmentation networks to the HSS setting, and how to leverage the hierarchy information to regularize HSS network learning.
- Face Forensics in the Wild195
This work constructs a novel large-scale dataset, called FFIW10K, which comprises 10,000 high-quality forgery videos, with an average of three human faces in each frame, and proposes a novel algorithm to tackle the task of multi-person face forgery detection.
- Learning Video Object Segmentation From Unlabeled Videos184
A unified unsupervised/weakly supervised learning framework, called MuG, that comprehensively captures intrinsic properties of VOS at multiple granularities is introduced that can help advance understanding of visual patterns in VOS and significantly reduce annotation burden.
- Structured Scene Memory for Vision-Language Navigation171
This work proposes a crucial architecture, called Structured Scene Memory (SSM), which is compartmentalized enough to accurately memorize the percepts during navigation and serves as a structured scene representation, which captures and disentangles visual and geometric cues in the environment.
- 161
- 161
- 157
- Learning Descriptor Networks for 3D Shape Synthesis and Analysis157
A 3D shape descriptor network, which is a deep convolutional energy-based model, for modeling volumetric shape patterns and can be used to train a 3D generator network via MCMC teaching.
- 156
- 156
- IS-Fusion: Instance-Scene Collaborative Fusion for Multimodal 3D Object Detection150
IS-Fusion is proposed, an innovative multimodal fusion framework that jointly captures the Instance- and Scene-level contextual information and outperforms all the published multimodal works to date.
- 147
- 144
- 142
- Learning Compositional Neural Information Fusion for Human Parsing141
This work proposes to combine neural networks with the compositional hierarchy of human bodies for efficient and complete human parsing, formulate the approach as a neural information fusion framework that is extensively evaluated on four popular datasets.
- 137
- Understanding Human Gaze Communication by Spatio-Temporal Graph Reasoning133
A spatio-temporal graph neural network is proposed to explicitly represent the diverse gaze interactions in the social scenes and to infer atomic- level gaze communication by message passing and an event network with encoder-decoder structure to predict the event-level gaze communication.
- Dreamwalker: Mental Planning for Continuous Vision-Language Navigation130
This work proposes Dreamwalker — a world model based VLN-CE agent, built to summarize the visual, topological, and dynamic properties of the complicated continuous environment into a discrete, structured, and compact representation.
- Cascaded Human-Object Interaction Recognition130
This work introduces a cascade architecture for a multi-stage, coarse-to-fine HOI understanding, and makes the framework flexible to perform fine-grained pixel-wise relation segmentation; this provides a new glimpse into better relation modeling.
- Paying Attention to Video Object Pattern Understanding128
For the first time, it is quantitatively verified the high consistency of visual attention behavior among human observers, and found strong correlation between human attention and explicit primary object judgments during dynamic, task-driven viewing.
- Weakly Supervised 3D Object Detection from Lidar Point Cloud127
This work proposes a weakly supervised approach for 3D object detection, only requiring a small set of weakly annotated scenes, associated with a few precisely labeled object instances, achieved by a two-stage architecture design.
- Reasoning Visual Dialogs With Structural and Partial Observations124
This paper introduces an Expectation Maximization algorithm to infer both the underlying dialog structures and the missing node values (desired answers) and proposes a differentiable graph neural network (GNN) solution that approximates this process.
- Local-Global Context Aware Transformer for Language-Guided Video Segmentation120
This work presents Locater, which augments the Transformer architecture with a finite memory so as to query the entire video with the language expression in an efficient manner, and outperforms previous state-of-the-arts solutions.
- Deep Cropping via Attention Box Prediction and Aesthetics Assessment120
A neural network is designed that has two branches for predicting attention bounding box and analyzing aesthetics, respectively that avoids repeated feature computation and leading to higher computation efficiency in photo cropping.
- Bird’s-Eye-View Scene Graph for Vision-Language Navigation119
This work presents a BEV Scene Graph (BSG), which leverages multi-step BEV representations to encode scene layouts and geometric cues of indoor environment under the supervision of 3D detection and significantly outperforms state-of-the-art methods on REVERIE, R2R, and R4R, showing the potential of BEV perception in VLN.
- 119
- A Unified Object Motion and Affinity Model for Online Multi-Object Tracking118
This paper proposes a novel MOT framework that unifies object motion and affinity model into a single network, named UMA, in order to learn a compact feature that is discriminative for both objectMotion and affinity measure.
- Hierarchical Human Parsing With Typed Part-Relation Reasoning115
This work seeks to simultaneously exploit the representational capacity of deep graph networks and the hierarchical human structures by assimilating generic message-passing networks with their edge-typed, convolutional counterparts and lays the foundation for more sophisticated and flexible human relation patterns of reasoning.
- Examining CNN Representations With Respect to Dataset Bias113
This paper proposes a simple yet effective method to diagnose feature representations of the CNN by comparing latent relationships between representations of different attributes inside the CNN to discover the CNN's blind spots and failure modes due to dataset bias.
- 113
- 103
- Volumetric Environment Representation for Vision-Language Navigation100
This work introduces a Volumetric Environ-ment Representation (VER), which voxelizes the physical world into structured 3D cells and achieves state-of-the-art performance across VLN benchmarks (R2R, REVERIE, and R4R).
- 99
- 99
- 97
- 96
- 96
- 93
- Target-Driven Structured Transformer Planner for Vision-Language Navigation89
This article devise an Imaginary Scene Tokenization mechanism for explicit estimation of the long-term target (even located in unexplored environments) and design a Structured Transformer Planner which elegantly incorporates the explored room layout into a neural attention architecture for structured and global planning.
- Active Visual Information Gathering for Vision-Language Navigation89
This work proposes an end-to-end framework for learning an exploration policy that decides i) when and where to explore, ii) what information is worth gathering during exploration, and iii) how to adjust the navigation decision after the exploration.
- 86
- Counterfactual Cycle-Consistent Learning for Instruction Following and Generation in Vision-Language Navigation86
This work describes an approach that learns the two tasks simultaneously and exploits their intrinsic correlations to boost the training of each: the follower judges whether the speaker-created instruction explains the original navigation route correctly, and vice versa.
- Optimizing the F-Measure for Threshold-Free Salient Object Detection86
The relaxed F-measure is proposed which is differentiable w.r.t the posterior and can be easily appended to the back of CNNs as the loss function, named FLoss, which can continuously force the network to produce polarized activations.
- 84
- 83
- Towards Data-And Knowledge-Driven AI: A Survey on Neuro-Symbolic Computing81
A systematic overview of the recent developments and important contributions of NeSy research is provided, including recent landmark approaches along several main characteristics that underline this research paradigm, including neural-symbolic integration, knowledge representation, knowledge embedding, and functionality.
- 80
- Differentiable Multi-Granularity Human Representation Learning for Instance-Aware Human Semantic Parsing78
A new bottom-up regime is proposed to learn category-level human semantic segmentation as well as multi- person pose estimation in a joint and end-to-end manner that exploits structural information over different human granularities and eases the difficulty of person partitioning.
- LANA: A Language-Capable Navigator for Instruction Following and Generation72
This article devise LANA, a language-capable navigation agent which is able to not only execute human-written navigation commands, but also provide route descriptions to humans, by simultaneously learning instruction following and generation with only one single model.
- 72
- 69
- 65
- Locality-Aware Inter-and Intra-Video Reconstruction for Self-Supervised Correspondence Learning63
Lir is developed, a locality-aware inter-and intra-video reconstruction method that fills in three missing pieces, i.e., instance discrimination, location awareness, and spatial compactness, of self-supervised correspondence learning puzzle, and surpasses self- supervised state-of-the-arts on label propagation tasks including objects, semantic parts, and keypoints.
- Logic-induced Diagnostic Reasoning for Semi-supervised Semantic Segmentation62
LogicDiag, a brand new neural-logic semi-supervised learning framework that formalizes the structured abstraction of semantic concepts as a set of logic rules, and highlights the promising opportunities arising from the systematic integration of symbolic reasoning into the prevalent statistical, neural learning approaches.
- Collaborative Spatial-Temporal Modeling for Language-Queried Video Actor Segmentation61
This work proposes a collaborative spatial-temporal encoder-decoder framework which contains a 3D temporal encoder over the video clip to recognize the queried actions, and a 2D spatial encoding over the target frame to accurately segment the querying actors.
- Visual Abductive Reasoning59
A new task and dataset, Visual Abductive Reasoning (VAR), for examining abductive reasoning ability of machine intelligence in everyday visual situations, and devise a strong baseline model, REASONER (causal-and-cascaded reasoning Transformer), which surpasses many famous video-language models, while still being far behind human performance.
- Clustering based Point Cloud Representation Learning for 3D Analysis57
This work proposes a clustering based supervised learning scheme for point cloud analysis that conducts within-class clustering on the point embedding space for automatically discovering subclass patterns which are latent yet representative across scenes.
- LogicSeg: Parsing Visual Semantics with Neural Logic Learning and Reasoning53
LogicSeg is a holistic visual semantic parser that integrates neural inductive learning and logic reasoning with both rich data and symbolic knowledge, and is believed to open a new avenue for visual semantic parsing.
- Boosting Video Object Segmentation via Space-Time Correspondence Learning51
This work devise a correspondence-aware training framework, which boosts matching-based VOS solutions by explicitly encouraging robust correspondence matching during network learning, and reinforces the standard, fully supervised training of mask segmentation with label-free, contrastive correspondence learning.
- 50
- Super-Trajectory for Video Segmentation50
A novel semi-supervised video segmentation approach based on an efficient video representation, called as “super-trajectory”, which is capable of distinguishing the target objects from complex backgrounds and even reidentifying them after occlusions.
- GeneSegNet: a deep learning framework for cell segmentation by integrating gene expression and imaging49
This work developed a deep-learning-based method, GeneSegNet, that integrates both gene expression and imaging information to perform cell segmentation and employs a recursive training strategy to deal with noisy training labels.
- Scalable Video Object Segmentation With Identification Mechanism47
Two innovative approaches to scalable and effective multi-object modeling for semi-supervised Video Object Segmentation (VOS) are presented, Associating Objects with Transformers (AOT) and Associating Objects with Scalable Transformers (AOST), which display exceptional efficiency and scalability consistently across all six benchmarks.
- 47
- 45
- 45
- Large-Scale Person Detection and Localization using Overhead Fisheye Cameras42
This article presents LOAF, the first large-scale overhead fisheye dataset for person detection and localization, and builds a fisheye person detection network, which exploits the fisheye distortions by a rotation-equivariant training strategy and predict radius-aligned human boxes end-to-end.
- 42
- 41
- Clustering Propagation for Universal Medical Image Segmentation35
S2VNet is introduced, a universal framework that leverages Slice-to- Volume propagation to unify auto-matic/interactive segmentation within a single model and one training session, and surpasses task-specified solutions on both automatic/interactive setups.
- 34
- 31
- 30
- 29
- 29
- Spatio-Temporal Decoupled Knowledge Compensator for Few-Shot Action Recognition26
DiST, an innovative Decomposition-incorporation framework for FSAR that makes use of decoupled Spatial and Temporal knowledge provided by large language models to learn expressive multi-granularity prototypes, is proposed.
- 26
- 26
- 25
- 25
- 23
- 22
- 20
- 20
- 19
- 18
- 18
- 18
- 17
- 16
- 16
- 15
- 15
- Clustering for Protein Representation Learning14
A neural clustering framework that can automatically discover the critical components of a protein by considering both its primary and tertiary structure information and achieves state-of-the-art performance.
- 13
- 13
- 13
- 11
- 11
- 10
- 10
- 10
- 9
- 9
- 8
- 8
- 8
- 7
- 7
- 7
- 7
- 6
- 6
- 5
- 5
- 5
- 4
- Improving Neural Machine Translation by Achieving Knowledge Transfer with Sentence Alignment Learning4
This work designs a discriminator that learns to estimate sentence aligning score over translation candidates, and then the learned semantic knowledge is transfered to the NMT model under an adversarial learning framework and proposes a gated self-attention based encoder for sentence embedding.
- 4
- 3
- 3
- 3
- 3
- 3
- 2
- 2
- 2
- 2
- 1
- Chemical knowledge-informed framework for privacy-aware retrosynthesis learning1
The chemical knowledge-informed framework (CKIF), a privacy-preserving approach for learning retrosynthesis models, is introduced, enabling organisations to collaboratively train retrosynthesis models without sharing raw data.
- 1
- 1
- 1
- Video Object Segmentation via Super-trajectories1
A novel semi-supervised video segmentation approach based on an efficient video representation, called as "super-trajectory", which corresponds to a group of compact trajectories that exhibit consistent motion patterns, similar appearance and close spatiotemporal relationships.
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- Selective Video Cutout using Global Pyramid Models and Local Uncertainty Propagation.–
A pyramid histogram based confidence map that incorporates structure information into appearance statistics that combines geodesic distance based dynamic models and employs an efficient measure of uncertainty propagation using local classifiers to determine the image regions where the object labels might be ambiguous.
- –
- –
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 2026-10-13. 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.