Search Results for author:
Found 53 papers, 30 papers with code
MultiConIR: Towards multi-condition Information Retrieval
In this paper, we introduce MultiConIR, the first benchmark designed to evaluate retrieval models in multi-condition scenarios.
Integrating Chain-of-Thought for Multimodal Alignment: A Study on 3D Vision-Language Learning
Chain-of-Thought (CoT) reasoning has proven effective in natural language tasks but remains underexplored in multimodal alignment.
Unveiling the Key Factors for Distilling Chain-of-Thought Reasoning
Large Language Models (LLMs) excel in reasoning tasks through Chain-of-Thought (CoT) prompting.
GenVidBench: A Challenging Benchmark for Detecting AI-Generated Video
We conduct a comprehensive evaluation of different advanced video generators and present a challenging setting.
Align-KD: Distilling Cross-Modal Alignment Knowledge for Mobile Vision-Language Model
The teacher also helps student learn the projection of vision token into text embedding space based on the focus of text.
TinyViM: Frequency Decoupling for Tiny Hybrid Vision Mamba
Based on the analyses, we introduce a novel Laplace mixer to decouple the features in terms of frequency and input only the low-frequency components into the Mamba block.
Fine-Grained and Multi-Dimensional Metrics for Document-Level Machine Translation
This work investigates the inherent capability of instruction-tuned LLMs for document-level translation (docMT).
The Accuracy Paradox in RLHF: When Better Reward Models Don't Yield Better Language Models
Reinforcement Learning from Human Feedback significantly enhances Natural Language Processing by aligning language models with human expectations.
Full-Stage Pseudo Label Quality Enhancement for Weakly-supervised Temporal Action Localization
However, the quality of pseudo labels in the framework, which is a key factor to the final result, is not carefully studied.
ExCP: Extreme LLM Checkpoint Compression via Weight-Momentum Joint Shrinking
For instance, we achieve approximately $70\times$ compression for the Pythia-410M model, with the final performance being as accurate as the original model on various downstream tasks.
GeminiFusion: Efficient Pixel-wise Multimodal Fusion for Vision Transformer
Cross-modal transformers have demonstrated superiority in various vision tasks by effectively integrating different modalities.
Ranked #1 on
Semantic Segmentation
on SUN-RGBD
SLAB: Efficient Transformers with Simplified Linear Attention and Progressive Re-parameterized Batch Normalization
However, replacing LayerNorm with more efficient BatchNorm in transformer often leads to inferior performance and collapse in training.
No Time to Waste: Squeeze Time into Channel for Mobile Video Understanding
In this paper, we propose to squeeze the time axis of a video sequence into the channel dimension and present a lightweight video recognition network, term as \textit{SqueezeTime}, for mobile video understanding.
SSA-Seg: Semantic and Spatial Adaptive Pixel-level Classifier for Semantic Segmentation
Specifically, we employ the coarse masks obtained from the fixed prototypes as a guide to adjust the fixed prototype towards the center of the semantic and spatial domains in the test image.
Context-Guided Spatial Feature Reconstruction for Efficient Semantic Segmentation
A shape self-calibration function is designed to make the key areas closer to foreground objects.
TinySAM: Pushing the Envelope for Efficient Segment Anything Model
Massive following works have developed various applications based on the pre-trained SAM and achieved impressive performance on downstream vision tasks.
PPT: Token Pruning and Pooling for Efficient Vision Transformers
Vision Transformers (ViTs) have emerged as powerful models in the field of computer vision, delivering superior performance across various vision tasks.
Ranked #4 on
Efficient ViTs
on ImageNet-1K (with DeiT-S)
Less is More: Focus Attention for Efficient DETR
DETR-like models have significantly boosted the performance of detectors and even outperformed classical convolutional models.
BiMLP: Compact Binary Architectures for Vision Multi-Layer Perceptrons
This paper studies the problem of designing compact binary architectures for vision multi-layer perceptrons (MLPs).
AdaBin: Improving Binary Neural Networks with Adaptive Binary Sets
Since the modern deep neural networks are of sophisticated design with complex architecture for the accuracy reason, the diversity on distributions of weights and activations is very high.
Spatial-Channel Token Distillation for Vision MLPs
Recently, neural architectures with all Multi-layer Perceptrons (MLPs) have attracted great research interest from the computer vision community.
Ranked #538 on
Image Classification
on ImageNet
Multimodal Token Fusion for Vision Transformers
Many adaptations of transformers have emerged to address the single-modal vision tasks, where self-attention modules are stacked to handle input sources like images.
Ranked #4 on
Semantic Segmentation
on LLRGBD-synthetic
MaskGroup: Hierarchical Point Grouping and Masking for 3D Instance Segmentation
For instance, our approach achieves a 66. 4\% mAP with the 0. 5 IoU threshold on the ScanNetV2 test set, which is 1. 9\% higher than the state-of-the-art method.
Ranked #7 on
3D Instance Segmentation
on S3DIS
AutoLoss-GMS: Searching Generalized Margin-Based Softmax Loss Function for Person Re-Identification
In this paper, we propose a novel method, AutoLoss-GMS, to search the better loss function in the space of generalized margin-based softmax loss function for person re-identification automatically.
An Empirical Study of Adder Neural Networks for Object Detection
Adder neural networks (AdderNets) have shown impressive performance on image classification with only addition operations, which are more energy efficient than traditional convolutional neural networks built with multiplications.
Towards Stable and Robust AdderNets
Adder neural network (AdderNet) replaces the original convolutions with massive multiplications by cheap additions while achieving comparable performance thus yields a series of energy-efficient neural networks.
Handling Long-tailed Feature Distribution in AdderNets
Adder neural networks (ANNs) are designed for low energy cost which replace expensive multiplications in convolutional neural networks (CNNs) with cheaper additions to yield energy-efficient neural networks and hardware accelerations.
Hire-MLP: Vision MLP via Hierarchical Rearrangement
Previous vision MLPs such as MLP-Mixer and ResMLP accept linearly flattened image patches as input, making them inflexible for different input sizes and hard to capture spatial information.
CMT: Convolutional Neural Networks Meet Vision Transformers
Vision transformers have been successfully applied to image recognition tasks due to their ability to capture long-range dependencies within an image.
Positive-Unlabeled Data Purification in the Wild for Object Detection
In this paper, we present a positive-unlabeled learning based scheme to expand training data by purifying valuable images from massive unlabeled ones, where the original training data are viewed as positive data and the unlabeled images in the wild are unlabeled data.
Data-Free Knowledge Distillation for Image Super-Resolution
Experiments on various datasets and architectures demonstrate that the proposed method is able to be utilized for effectively learning portable student networks without the original data, e. g., with 0. 16dB PSNR drop on Set5 for x2 super resolution.
Winograd Algorithm for AdderNet
Adder neural network (AdderNet) is a new kind of deep model that replaces the original massive multiplications in convolutions by additions while preserving the high performance.
Distilling Object Detectors via Decoupled Features
To this end, we present a novel distillation algorithm via decoupled features (DeFeat) for learning a better student detector.
A Survey on Visual Transformer
Transformer, first applied to the field of natural language processing, is a type of deep neural network mainly based on the self-attention mechanism.
VEGA: Towards an End-to-End Configurable AutoML Pipeline
Automated Machine Learning (AutoML) is an important industrial solution for automatic discovery and deployment of the machine learning models.
Kernel Based Progressive Distillation for Adder Neural Networks
A convolutional neural network (CNN) with the same architecture is simultaneously initialized and trained as a teacher network, features and weights of ANN and CNN will be transformed to a new space to eliminate the accuracy drop.
MTP: Multi-Task Pruning for Efficient Semantic Segmentation Networks
To identify the redundancy in segmentation networks, we present a multi-task channel pruning approach.
Optical Flow Distillation: Towards Efficient and Stable Video Style Transfer
This paper proposes to learn a lightweight video style transfer network via knowledge distillation paradigm.
HourNAS: Extremely Fast Neural Architecture Search Through an Hourglass Lens
To achieve an extremely fast NAS while preserving the high accuracy, we propose to identify the vital blocks and make them the priority in the architecture search.
Hit-Detector: Hierarchical Trinity Architecture Search for Object Detection
To this end, we propose a hierarchical trinity search framework to simultaneously discover efficient architectures for all components (i. e. backbone, neck, and head) of object detector in an end-to-end manner.
CARS: Continuous Evolution for Efficient Neural Architecture Search
Architectures in the population that share parameters within one SuperNet in the latest generation will be tuned over the training dataset with a few epochs.
Bi-stream Pose Guided Region Ensemble Network for Fingertip Localization from Stereo Images
To mitigate these limitations and promote further research on hand pose estimation from stereo images, we propose a new large-scale binocular hand pose dataset called THU-Bi-Hand, offering a new perspective for fingertip localization.
Motion feature augmented network for dynamic hand gesture recognition from skeletal data
Dynamic hand gesture recognition has attracted increasing attention because of its importance for human–computer interaction.
SHPR-Net: Deep Semantic Hand Pose Regression From Point Clouds
The semantic segmentation network assigns semantic labels for each point in the point set.
Ranked #7 on
Hand Pose Estimation
on MSRA Hands
Two-Stream Binocular Network: Accurate Near Field Finger Detection Based On Binocular Images
Different from previous works, we propose a new framework, named Two-Stream Binocular Network (TSBnet) to detect fingertips from binocular images directly.
Interactive Hand Pose Estimation: Boosting accuracy in localizing extended finger joints
In the reality of HMI, joints in fingers stretching out, especially corresponding fingertips, are much more important than other joints.
Depth-Based 3D Hand Pose Estimation: From Current Achievements to Future Goals
Official Torch7 implementation of "V2V-PoseNet: Voxel-to-Voxel Prediction Network for Accurate 3D Hand and Human Pose Estimation from a Single Depth Map", CVPR 2018
Ranked #5 on
Hand Pose Estimation
on HANDS 2017
Pose Guided Structured Region Ensemble Network for Cascaded Hand Pose Estimation
The proposed method extracts regions from the feature maps of convolutional neural network under the guide of an initially estimated pose, generating more optimal and representative features for hand pose estimation.
Ranked #8 on
Hand Pose Estimation
on HANDS 2017
Motion Feature Augmented Recurrent Neural Network for Skeleton-based Dynamic Hand Gesture Recognition
Dynamic hand gesture recognition has attracted increasing interests because of its importance for human computer interaction.
Ranked #9 on
Hand Gesture Recognition
on DHG-28
Towards Good Practices for Deep 3D Hand Pose Estimation
3D hand pose estimation from single depth image is an important and challenging problem for human-computer interaction.
Ranked #4 on
Pose Estimation
on ITOP top-view
Region Ensemble Network: Improving Convolutional Network for Hand Pose Estimation
Hand pose estimation from monocular depth images is an important and challenging problem for human-computer interaction.
Ranked #11 on
Hand Pose Estimation
on MSRA Hands
Two-stream convolutional neural network for accurate RGB-D fingertip detection using depth and edge information
Accurate detection of fingertips in depth image is critical for human-computer interaction.
