Search Results for author:
Found 33 papers, 13 papers with code
Recent Advances in Multi-modal 3D Scene Understanding: A Comprehensive Survey and Evaluation
Multi-modal 3D scene understanding has gained considerable attention due to its wide applications in many areas, such as autonomous driving and human-computer interaction.
Vote2Cap-DETR++: Decoupling Localization and Describing for End-to-End 3D Dense Captioning
Moreover, we argue that object localization and description generation require different levels of scene understanding, which could be challenging for a shared set of queries to capture.
Unsupervised Domain Adaptation via Domain-Adaptive Diffusion
Unsupervised Domain Adaptation (UDA) is quite challenging due to the large distribution discrepancy between the source domain and the target domain.
Unsupervised Image Denoising in Real-World Scenarios via Self-Collaboration Parallel Generative Adversarial Branches
Although unsupervised approaches based on generative adversarial networks offer a promising solution for denoising without paired datasets, they are difficult in surpassing the performance limitations of conventional GAN-based unsupervised frameworks without significantly modifying existing structures or increasing the computational complexity of denoisers.
End-to-End 3D Dense Captioning with Vote2Cap-DETR
Compared with prior arts, our framework has several appealing advantages: 1) Without resorting to numerous hand-crafted components, our method is based on a full transformer encoder-decoder architecture with a learnable vote query driven object decoder, and a caption decoder that produces the dense captions in a set-prediction manner.
Zero-Shot Point Cloud Segmentation by Semantic-Visual Aware Synthesis
Given only the class-level semantic information for unseen objects, we strive to enhance the correspondence, alignment and consistency between the visual and semantic spaces, to synthesise diverse, generic and transferable visual features.
Geometry and Uncertainty-Aware 3D Point Cloud Class-Incremental Semantic Segmentation
Despite the significant recent progress made on 3D point cloud semantic segmentation, the current methods require training data for all classes at once, and are not suitable for real-life scenarios where new categories are being continuously discovered.
Context-Aware Alignment and Mutual Masking for 3D-Language Pre-Training
The current approaches for 3D visual reasoning are task-specific, and lack pre-training methods to learn generic representations that can transfer across various tasks.
ZegCLIP: Towards Adapting CLIP for Zero-shot Semantic Segmentation
Recently, CLIP has been applied to pixel-level zero-shot learning tasks via a two-stage scheme.
Pretrained Language Encoders are Natural Tagging Frameworks for Aspect Sentiment Triplet Extraction
Existing works usually formulate the span detection as a 1D token tagging problem, and model the sentiment recognition with a 2D tagging matrix of token pairs.
Semantic-Aware Domain Generalized Segmentation
In this paper, we address domain generalized semantic segmentation, where a segmentation model is trained to be domain-invariant without using any target domain data.
Deformation and Correspondence Aware Unsupervised Synthetic-to-Real Scene Flow Estimation for Point Clouds
With that, we develop a large-scale synthetic scene flow dataset GTA-SF.
Box2Seg: Learning Semantics of 3D Point Clouds with Box-Level Supervision
In this paper, we introduce a neural architecture, termed Box2Seg, to learn point-level semantics of 3D point clouds with bounding box-level supervision.
Overcome Anterograde Forgetting with Cycled Memory Networks
This work proposes a general framework named Cycled Memory Networks (CMN) to address the anterograde forgetting in neural networks for lifelong learning.
Mind Your Clever Neighbours: Unsupervised Person Re-identification via Adaptive Clustering Relationship Modeling
To generate high-quality pseudo-labels and mitigate the impact of clustering errors, we propose a novel clustering relationship modeling framework for unsupervised person Re-ID.
Reviewing continual learning from the perspective of human-level intelligence
Different from previous reviews that mainly focus on the catastrophic forgetting phenomenon in CL, this paper surveys CL from a more macroscopic perspective based on the Stability Versus Plasticity mechanism.
Global and Local Texture Randomization for Synthetic-to-Real Semantic Segmentation
In this work, we propose two simple yet effective texture randomization mechanisms, Global Texture Randomization (GTR) and Local Texture Randomization (LTR), for Domain Generalization based SRSS.
Sparse-to-dense Feature Matching: Intra and Inter domain Cross-modal Learning in Domain Adaptation for 3D Semantic Segmentation
Domain adaptation is critical for success when confronting with the lack of annotations in a new domain.
A Generalized Framework for Edge-preserving and Structure-preserving Image Smoothing
The effectiveness and superior performance of our approach are validated through comprehensive experiments in a range of applications.
Hierarchical Paired Channel Fusion Network for Street Scene Change Detection
Based on the MPFL strategy, our framework achieves a novel approach to adapt to the scale and location diversities of the scene change regions.
Contextualize Knowledge Bases with Transformer for End-to-end Task-Oriented Dialogue Systems
Incorporating knowledge bases (KB) into end-to-end task-oriented dialogue systems is challenging, since it requires to properly represent the entity of KB, which is associated with its KB context and dialogue context.
Ranked #2 on
Task-Oriented Dialogue Systems
on KVRET
Semantic Context Encoding for Accurate 3D Point Cloud Segmentation
In this paper, we propose a simple yet effective Point Context Encoding (PointCE) module to capture semantic contexts of a point cloud and adaptively highlight intermediate feature maps.
Semi-Supervised Crowd Counting via Self-Training on Surrogate Tasks
Most existing crowd counting systems rely on the availability of the object location annotation which can be expensive to obtain.
Global context reasoning for semantic segmentation of 3d point clouds
In this paper, we propose a Point Global Context Reasoning (PointGCR) module to capture global contextual information along the channel dimension.
Towards Using Count-level Weak Supervision for Crowd Counting
Most existing crowd counting methods require object location-level annotation, i. e., placing a dot at the center of an object.
Overcoming Long-term Catastrophic Forgetting through Adversarial Neural Pruning and Synaptic Consolidation
It is due to two facts: first, as the model learns more tasks, the intersection of the low-error parameter subspace satisfying for these tasks becomes smaller or even does not exist; second, when the model learns a new task, the cumulative error keeps increasing as the model tries to protect the parameter configuration of previous tasks from interference.
Improving Distant Supervised Relation Extraction by Dynamic Neural Network
To account for this style shift, the model should adjust its parameters in accordance with entity types.
Deep Multiphase Level Set for Scene Parsing
The proposed method consists of three modules, i. e., recurrent FCNs, adaptive multiphase level set, and deeply supervised learning.
Cascaded Context Pyramid for Full-Resolution 3D Semantic Scene Completion
To address these issues, in this work we propose a novel deep learning framework, named Cascaded Context Pyramid Network (CCPNet), to jointly infer the occupancy and semantic labels of a volumetric 3D scene from a single depth image.
Ranked #5 on
3D Semantic Scene Completion
on NYUv2
(using extra training data)
A Generalized Framework for Edge-preserving and Structure-preserving Image Smoothing
In this paper, a non-convex non-smooth optimization framework is proposed to achieve diverse smoothing natures where even contradictive smoothing behaviors can be achieved.
A Sketch Based 3D Shape Retrieval Approach Based on Efficient Deep Point-to-Subspace Metric Learning
A sketch based 3D shape retrieval
Mask-aware networks for crowd counting
Our rationale is that the mask prediction could be better modeled as a binary segmentation problem and the difficulty of estimating the density could be reduced if the mask is known.
Non-rigid Object Tracking via Deep Multi-scale Spatial-temporal Discriminative Saliency Maps
Extensive experiments demonstrate that the proposed algorithm achieves competitive performance in both saliency detection and visual tracking, especially outperforming other related trackers on the non-rigid object tracking datasets.
