Search Results for author:
Found 42 papers, 14 papers with code
Variance-Dependent Regret Bounds for Non-stationary Linear Bandits
We investigate the non-stationary stochastic linear bandit problem where the reward distribution evolves each round.
Federated Contextual Cascading Bandits with Asynchronous Communication and Heterogeneous Users
We study the problem of federated contextual combinatorial cascading bandits, where $|\mathcal{U}|$ agents collaborate under the coordination of a central server to provide tailored recommendations to the $|\mathcal{U}|$ corresponding users.
Design Your Own Universe: A Physics-Informed Agnostic Method for Enhancing Graph Neural Networks
Physics-informed Graph Neural Networks have achieved remarkable performance in learning through graph-structured data by mitigating common GNN challenges such as over-smoothing, over-squashing, and heterophily adaption.
Exploring Self- and Cross-Triplet Correlations for Human-Object Interaction Detection
In this work, we propose to explore Self- and Cross-Triplet Correlations (SCTC) for HOI detection.
Human-Object Interaction Detection
Knowledge Distillation
+2
XAI for In-hospital Mortality Prediction via Multimodal ICU Data
To address this issue, this paper proposes an eXplainable Multimodal Mortality Predictor (X-MMP) approaching an efficient, explainable AI solution for predicting in-hospital mortality via multimodal ICU data.
SurgicalPart-SAM: Part-to-Whole Collaborative Prompting for Surgical Instrument Segmentation
Specifically, we achieve this by proposing (1) Collaborative Prompts that describe instrument structures via collaborating category-level and part-level texts; (2) Cross-Modal Prompt Encoder that encodes text prompts jointly with visual embeddings into discriminative part-level representations; and (3) Part-to-Whole Adaptive Fusion and Hierarchical Decoding that adaptively fuse the part-level representations into a whole for accurate instrument segmentation in surgical scenarios.
HGCLIP: Exploring Vision-Language Models with Graph Representations for Hierarchical Understanding
We explore constructing the class hierarchy into a graph, with its nodes representing the textual or image features of each category.
Fine-Grained Visual Recognition
Graph Representation Learning
Autoregressive Omni-Aware Outpainting for Open-Vocabulary 360-Degree Image Generation
A 360-degree (omni-directional) image provides an all-encompassing spherical view of a scene.
The FruitShell French synthesis system at the Blizzard 2023 Challenge
The evaluation results of our system showed a quality MOS score of 3. 6 for the Hub task and 3. 4 for the Spoke task, placing our system at an average level among all participating teams.
Terrain Diffusion Network: Climatic-Aware Terrain Generation with Geological Sketch Guidance
Sketch-based terrain generation seeks to create realistic landscapes for virtual environments in various applications such as computer games, animation and virtual reality.
Bridging the Gap: Fine-to-Coarse Sketch Interpolation Network for High-Quality Animation Sketch Inbetweening
The 2D animation workflow is typically initiated with the creation of keyframes using sketch-based drawing.
Robust Audio Anti-Spoofing with Fusion-Reconstruction Learning on Multi-Order Spectrograms
Robust audio anti-spoofing has been increasingly challenging due to the recent advancements on deepfake techniques.
SurgicalSAM: Efficient Class Promptable Surgical Instrument Segmentation
However, we observe two problems with this naive pipeline: (1) the domain gap between natural objects and surgical instruments leads to inferior generalisation of SAM; and (2) SAM relies on precise point or box locations for accurate segmentation, requiring either extensive manual guidance or a well-performing specialist detector for prompt preparation, which leads to a complex multi-stage pipeline.
When Deep Learning Meets Multi-Task Learning in SAR ATR: Simultaneous Target Recognition and Segmentation
In this paper, we propose a new multi-task learning approach for SAR ATR, which could obtain the accurate category and precise shape of the targets simultaneously.
LAMM: Language-Assisted Multi-Modal Instruction-Tuning Dataset, Framework, and Benchmark
To the best of our knowledge, we present one of the very first open-source endeavors in the field, LAMM, encompassing a Language-Assisted Multi-Modal instruction tuning dataset, framework, and benchmark.
Efficient and Interpretable Compressive Text Summarisation with Unsupervised Dual-Agent Reinforcement Learning
Recently, compressive text summarisation offers a balance between the conciseness issue of extractive summarisation and the factual hallucination issue of abstractive summarisation.
Full Resolution Repetition Counting
Given an untrimmed video, repetitive actions counting aims to estimate the number of repetitions of class-agnostic actions.
DSMNet: Deep High-precision 3D Surface Modeling from Sparse Point Cloud Frames
Second, we propose an modeling evaluation method based on HPMB for object-level modeling to overcome this limitation.
Point Cloud Registration
Simultaneous Localization and Mapping
Continuous Intermediate Token Learning with Implicit Motion Manifold for Keyframe Based Motion Interpolation
Deriving sophisticated 3D motions from sparse keyframes is a particularly challenging problem, due to continuity and exceptionally skeletal precision.
Multi-Scale Control Signal-Aware Transformer for Motion Synthesis without Phase
As past poses often contain useful auxiliary hints, in this paper, we propose a task-agnostic deep learning method, namely Multi-scale Control Signal-aware Transformer (MCS-T), with an attention based encoder-decoder architecture to discover the auxiliary information implicitly for synthesizing controllable motion without explicitly requiring auxiliary information such as phase.
Efficient Explorative Key-term Selection Strategies for Conversational Contextual Bandits
To tackle these issues, we first propose ``ConLinUCB", a general framework for conversational bandits with better information incorporation, combining arm-level and key-term-level feedback to estimate user preference in one step at each time.
Robust Knowledge Adaptation for Federated Unsupervised Person ReID
Thus, in this work, a federated unsupervised cluster-contrastive (FedUCC) learning method is proposed for Person ReID.
VAPCNet: Viewpoint-Aware 3D Point Cloud Completion
In this paper, we thus propose an unsupervised viewpoint representation learning scheme for 3D point cloud completion without explicit viewpoint estimation.
Towards Efficient Visual Simplification of Computational Graphs in Deep Neural Networks
A computational graph in a deep neural network (DNN) denotes a specific data flow diagram (DFD) composed of many tensors and operators.
TLDW: Extreme Multimodal Summarisation of News Videos
Multimodal summarisation with multimodal output is drawing increasing attention due to the rapid growth of multimedia data.
Multi-level Adversarial Spatio-temporal Learning for Footstep Pressure based FoG Detection
The proposed scheme also sheds light on improving subject-level clinical studies from other scenarios as it can be integrated with many existing deep architectures.
Skin Lesion Recognition with Class-Hierarchy Regularized Hyperbolic Embeddings
Accordingly, the learned prototypes preserve the semantic class relations in the embedding space and we can predict the label of an image by assigning its feature to the nearest hyperbolic class prototype.
Deep Laparoscopic Stereo Matching with Transformers
The self-attention mechanism, successfully employed with the transformer structure is shown promise in many computer vision tasks including image recognition, and object detection.
Action Recognition With Motion Diversification and Dynamic Selection
To address this issue, we introduce a Motion Diversification and Selection (MoDS) module to generate diversified spatio-temporal motion features and then select the suitable motion representation dynamically for categorizing the input video.
Ranked #18 on
Action Recognition
on Something-Something V1
1Cademy at Semeval-2022 Task 1: Investigating the Effectiveness of Multilingual, Multitask, and Language-Agnostic Tricks for the Reverse Dictionary Task
This paper describes our system for the SemEval2022 task of matching dictionary glosses to word embeddings.
OTExtSum: Extractive Text Summarisation with Optimal Transport
Optimal sentence extraction is conceptualised as obtaining an optimal summary that minimises the transportation cost to a given document regarding their semantic distributions.
LiDARCap: Long-range Marker-less 3D Human Motion Capture with LiDAR Point Clouds
Quantitative and qualitative experiments show that our method outperforms the techniques based only on RGB images.
Ranked #3 on
3D Human Pose Estimation
on SLOPER4D
(using extra training data)
Sign Language Translation with Hierarchical Spatio-TemporalGraph Neural Network
Therefore, in this paper, these unique characteristics of sign languages are formulated as hierarchical spatio-temporal graph representations, including high-level and fine-level graphs of which a vertex characterizes a specified body part and an edge represents their interactions.
Deep Learning Techniques for In-Crop Weed Identification: A Review
Weeds are a significant threat to the agricultural productivity and the environment.
Disentangling and Unifying Graph Convolutions for Skeleton-Based Action Recognition
Spatial-temporal graphs have been widely used by skeleton-based action recognition algorithms to model human action dynamics.
Ranked #4 on
3D Action Recognition
on Assembly101
Coupling Matrix Manifolds and Their Applications in Optimal Transport
These geometrical features of CMM have paved the way for developing numerical Riemannian optimization algorithms such as Riemannian gradient descent and Riemannian trust-region algorithms, forming a uniform optimization method for all types of OT problems.
IntersectGAN: Learning Domain Intersection for Generating Images with Multiple Attributes
For example, given two image domains $X_1$ and $X_2$ with certain attributes, the intersection $X_1 \cap X_2$ denotes a new domain where images possess the attributes from both $X_1$ and $X_2$ domains.
Realtime and Accurate 3D Eye Gaze Capture with DCNN-based Iris and Pupil Segmentation
A comparison against Wang et al.[3] shows that our method advances the state of the art in 3D eye tracking using a single RGB camera.
MRFalign: Protein Homology Detection through Alignment of Markov Random Fields
A sequence profile is usually represented as a position-specific scoring matrix (PSSM) or an HMM (Hidden Markov Model) and accordingly PSSM-PSSM or HMM-HMM comparison is used for homolog detection.
Protein Contact Prediction by Integrating Joint Evolutionary Coupling Analysis and Supervised Learning
To further improve the accuracy of the estimated precision matrices, we employ a supervised learning method to predict contact probability from a variety of evolutionary and non-evolutionary information and then incorporate the predicted probability as prior into our GGL framework.
Predicting protein contact map using evolutionary and physical constraints by integer programming (extended version)
Most existing methods predict the contact map matrix element-by-element, ignoring correlation among contacts and physical feasibility of the whole contact map.
