Search Results for author:
Found 55 papers, 19 papers with code
Hyperbolic Dual Feature Augmentation for Open-Environment
Feature augmentation generates novel samples in the feature space, providing an effective way to enhance the generalization ability of learning algorithms with hyperbolic geometry.
Multi-Sourced Compositional Generalization in Visual Question Answering
Compositional generalization is the ability of generalizing novel compositions from seen primitives, and has received much attention in vision-and-language (V\&L) recently.
Chain-of-Focus: Adaptive Visual Search and Zooming for Multimodal Reasoning via RL
Vision language models (VLMs) have achieved impressive performance across a variety of computer vision tasks.
Memory-Centric Embodied Question Answer
Unlike planner-centric EQA models where the memory module cannot fully interact with other modules, MemoryEQA flexible feeds memory information into all modules, thereby enhancing efficiency and accuracy in handling complex tasks, such as those involving multiple targets across different regions.
Multi-Label Stereo Matching for Transparent Scene Depth Estimation
To resolve the multi-label regression problem, we introduce a pixel-wise multivariate Gaussian representation, where the mean vector encodes multiple depth values at the same pixel, and the covariance matrix determines whether a multi-label representation is necessary for a given pixel.
Diving into the Fusion of Monocular Priors for Generalized Stereo Matching
A direct fusion of a monocular depth map could alleviate the local optima problem, but noisy disparity results computed at the first several iterations will misguide the fusion.
3D Visual Illusion Depth Estimation
3D visual illusion is a perceptual phenomenon where a two-dimensional plane is manipulated to simulate three-dimensional spatial relationships, making a flat artwork or object look three-dimensional in the human visual system.
Iterative Tool Usage Exploration for Multimodal Agents via Step-wise Preference Tuning
The data is subsequently used to update the controller for tool usage through preference tuning, producing a SPORT agent.
Large-Scale Riemannian Meta-Optimization via Subspace Adaptation
However, existing Riemannian meta-optimization methods take up huge memory footprints in large-scale optimization settings, as the learned optimizer can only adapt gradients of a fixed size and thus cannot be shared across different Riemannian parameters.
Multi-modal Agent Tuning: Building a VLM-Driven Agent for Efficient Tool Usage
The advancement of large language models (LLMs) prompts the development of multi-modal agents, which are used as a controller to call external tools, providing a feasible way to solve practical tasks.
Consistency of Compositional Generalization across Multiple Levels
Compositional generalization is the capability of a model to understand novel compositions composed of seen concepts.
World knowledge-enhanced Reasoning Using Instruction-guided Interactor in Autonomous Driving
The Multi-modal Large Language Models (MLLMs) with extensive world knowledge have revitalized autonomous driving, particularly in reasoning tasks within perceivable regions.
Residual Hyperbolic Graph Convolution Networks
In this paper, we propose residual hyperbolic graph convolutional networks (R-HGCNs) to address the over-smoothing problem.
FIRE: A Dataset for Feedback Integration and Refinement Evaluation of Multimodal Models
Vision language models (VLMs) have achieved impressive progress in diverse applications, becoming a prevalent research direction.
Temporally Consistent Stereo Matching
Based on this coherent state, we introduce a dual-space refinement module to iteratively refine the initialized result in both disparity and disparity gradient spaces, improving estimations in ill-posed regions.
SearchLVLMs: A Plug-and-Play Framework for Augmenting Large Vision-Language Models by Searching Up-to-Date Internet Knowledge
In this paper, we propose a plug-and-play framework, for augmenting existing LVLMs in handling visual question answering (VQA) about up-to-date knowledge, dubbed SearchLVLMs.
Vision Transformers for End-to-End Vision-Based Quadrotor Obstacle Avoidance
We demonstrate the capabilities of an attention-based end-to-end approach for high-speed vision-based quadrotor obstacle avoidance in dense, cluttered environments, with comparison to various state-of-the-art learning architectures.
DPGAN: A Dual-Path Generative Adversarial Network for Missing Data Imputation in Graphs
The crux of our work is that it admits both global and local representations of the input graph signal, which can capture the long-range dependencies.
Evaluating the Performance of ChatGPT for Spam Email Detection
This study provides insights into the potential and limitations of ChatGPT for spam identification, highlighting its potential as a viable solution for resource-constrained language domains.
Fine-Grained Annotation for Face Anti-Spoofing
In this paper, we propose a fine-grained annotation method for face anti-spoofing.
Neural 3D Scene Reconstruction from Multiple 2D Images without 3D Supervision
We improve the reconstruction quality of complex geometry scene regions with sparse depth obtained by using the geometric constraints.
Fast-StrucTexT: An Efficient Hourglass Transformer with Modality-guided Dynamic Token Merge for Document Understanding
Transformers achieve promising performance in document understanding because of their high effectiveness and still suffer from quadratic computational complexity dependency on the sequence length.
Exploring Data Geometry for Continual Learning
Our method dynamically expands the geometry of the underlying space to match growing geometric structures induced by new data, and prevents forgetting by keeping geometric structures of old data into account.
Marching-Primitives: Shape Abstraction from Signed Distance Function
Representing complex objects with basic geometric primitives has long been a topic in computer vision.
Exploring the Effect of Primitives for Compositional Generalization in Vision-and-Language
Compositional generalization is critical to simulate the compositional capability of humans, and has received much attention in the vision-and-language (V&L) community.
Parameterized Cost Volume for Stereo Matching
In this paper, we propose a parameterized cost volume to encode the entire disparity space using multi-Gaussian distribution.
Sparse Point Guided 3D Lane Detection
The high-resolution local information brought by sparse points refines 3D lanes in the BEV space hierarchically from low resolution to high resolution.
Video Anomaly Detection via Sequentially Learning Multiple Pretext Tasks
In this way, our method is able to reduce the difficulties of learning and avoid converging to sub-optimal solutions.
Primitive3D: 3D Object Dataset Synthesis from Randomly Assembled Primitives
Further study suggests that our strategy can improve the model performance by pretraining and fine-tuning scheme, especially for the dataset with a small scale.
Primitive-based Shape Abstraction via Nonparametric Bayesian Inference
In this paper, we propose a novel non-parametric Bayesian statistical method to infer an abstraction, consisting of an unknown number of geometric primitives, from a point cloud.
Global-Aware Registration of Less-Overlap RGB-D Scans
We propose a novel method of registering less-overlap RGB-D scans.
Maintaining Reasoning Consistency in Compositional Visual Question Answering
Existing VQA models can answer a compositional question well, but cannot work well in terms of reasoning consistency in answering the compositional question and its sub-questions.
Robust and Accurate Superquadric Recovery: a Probabilistic Approach
Among geometric primitives, superquadrics are well known for their ability to represent a wide range of shapes with few parameters.
Personalized Response Generation via Generative Split Memory Network
Despite the impressive successes of generation and dialogue systems, how to endow a text generation system with particular personality traits to deliver more personalized responses remains under-investigated.
GroupLink: An End-to-end Multitask Method for Word Grouping and Relation Extraction in Form Understanding
Forms are a common type of document in real life and carry rich information through textual contents and the organizational structure.
A Decomposition Model for Stereo Matching
In this paper, we present a decomposition model for stereo matching to solve the problem of excessive growth in computational cost (time and memory cost) as the resolution increases.
A Hyperbolic-to-Hyperbolic Graph Convolutional Network
Specifically, we developed a manifold-preserving graph convolution that consists of a hyperbolic feature transformation and a hyperbolic neighborhood aggregation.
Curvature Generation in Curved Spaces for Few-Shot Learning
Few-shot learning describes the challenging problem of recognizing samples from unseen classes given very few labeled examples.
SG-Net: Syntax Guided Transformer for Language Representation
In detail, for self-attention network (SAN) sponsored Transformer-based encoder, we introduce syntactic dependency of interest (SDOI) design into the SAN to form an SDOI-SAN with syntax-guided self-attention.
Campus3D: A Photogrammetry Point Cloud Benchmark for Hierarchical Understanding of Outdoor Scene
Based on it, we formulate a hierarchical learning problem for 3D point cloud segmentation and propose a measurement evaluating consistency across various hierarchies.
Content-Aware Inter-Scale Cost Aggregation for Stereo Matching
In this paper, we present a content-aware inter-scale cost aggregation method that adaptively aggregates and upsamples the cost volume from coarse-scale to fine-scale by learning dynamic filter weights according to the content of the left and right views on the two scales.
Semi-Supervised Models via Data Augmentationfor Classifying Interactive Affective Responses
We present semi-supervised models with data augmentation (SMDA), a semi-supervised text classification system to classify interactive affective responses.
On Isometry Robustness of Deep 3D Point Cloud Models under Adversarial Attacks
Armed with the Thompson Sampling, we develop a black-box attack with success rate over 95% on ModelNet40 data set.
Semantics-aware BERT for Language Understanding
The latest work on language representations carefully integrates contextualized features into language model training, which enables a series of success especially in various machine reading comprehension and natural language inference tasks.
Ranked #8 on
Natural Language Inference
on SNLI
DCMN+: Dual Co-Matching Network for Multi-choice Reading Comprehension
Multi-choice reading comprehension is a challenging task to select an answer from a set of candidate options when given passage and question.
SG-Net: Syntax-Guided Machine Reading Comprehension
In detail, for self-attention network (SAN) sponsored Transformer-based encoder, we introduce syntactic dependency of interest (SDOI) design into the SAN to form an SDOI-SAN with syntax-guided self-attention.
Ranked #5 on
Question Answering
on SQuAD2.0 dev
Stitching Videos from a Fisheye Lens Camera and a Wide-Angle Lens Camera for Telepresence Robots
In this paper, we propose to stitch videos from the FF-camera with a wide-angle lens and the DF-camera with a fisheye lens for telepresence robots.
Dual Co-Matching Network for Multi-choice Reading Comprehension
Multi-choice reading comprehension is a challenging task that requires complex reasoning procedure.
Ranked #3 on
Question Answering
on RACE
Auto-Retoucher(ART) - A framework for Background Replacement and Image Editing
Replacing the background and simultaneously adjusting foreground objects is a challenging task in image editing.
Explicit Contextual Semantics for Text Comprehension
Who did what to whom is a major focus in natural language understanding, which is right the aim of semantic role labeling (SRL) task.
Ranked #11 on
Natural Language Inference
on SNLI
Machine Reading Comprehension
Natural Language Understanding
+1
Deep Stereo Matching with Explicit Cost Aggregation Sub-Architecture
The cost aggregation sub-architecture is realized by a two-stream network: one for the generation of cost aggregation proposals, the other for the selection of the proposals.
Learning a Robust Representation via a Deep Network on Symmetric Positive Definite Manifolds
To this end, several new layers are introduced in our network, including a nonlinear kernel aggregation layer, an SPD matrix transformation layer, and a vectorization layer.
HOPE: Hierarchical Object Prototype Encoding for Efficient Object Instance Search in Videos
This paper tackles the problem of efficient and effective object instance search in videos.
A Hybrid Data Association Framework for Robust Online Multi-Object Tracking
In this paper, we present a hybrid data association framework with a min-cost multi-commodity network flow for robust online multi-object tracking.
