Search Results for author:
Found 21 papers, 11 papers with code
Reading Relevant Feature from Global Representation Memory for Visual Object Tracking
Therefore, using all features in the template and memory can lead to redundancy and impair tracking performance.
Weakly Supervised Gaussian Contrastive Grounding with Large Multimodal Models for Video Question Answering
GCG learns multiple Gaussian functions to characterize the temporal structure of the video, and sample question-critical frames as positive moments to be the visual inputs of LMMs.
Q&A Prompts: Discovering Rich Visual Clues through Mining Question-Answer Prompts for VQA requiring Diverse World Knowledge
With the breakthrough of multi-modal large language models, answering complex visual questions that demand advanced reasoning abilities and world knowledge has become a much more important testbed for developing AI models than ever.
Improving Empathetic Dialogue Generation by Dynamically Infusing Commonsense Knowledge
To this end, we propose a novel approach for empathetic response generation, which incorporates an adaptive module for commonsense knowledge selection to ensure consistency between the generated empathetic responses and the speaker's situation.
Correspondence Transformers With Asymmetric Feature Learning and Matching Flow Super-Resolution
The asymmetric feature learning module exploits a biased cross-attention mechanism to encode token features of source images with their target counterparts.
Hierarchical Visual Categories Modeling: A Joint Representation Learning and Density Estimation Framework for Out-of-Distribution Detection
We use one fold as the in-distribution dataset and the others as out-of-distribution datasets to evaluate the proposed method.
Weakly Supervised Learning of Semantic Correspondence through Cascaded Online Correspondence Refinement
Following the spirit of multiple instance learning (MIL), we decompose the weakly supervised correspondence learning problem into three stages: image-level matching, region-level matching, and pixel-level matching.
MISC210K: A Large-Scale Dataset for Multi-Instance Semantic Correspondence
Semantic correspondence have built up a new way for object recognition.
ColoristaNet for Photorealistic Video Style Transfer
The style removal network removes the original image styles, and the style restoration network recovers image styles in a supervised manner.
RankDNN: Learning to Rank for Few-shot Learning
This paper introduces a new few-shot learning pipeline that casts relevance ranking for image retrieval as binary ranking relation classification.
DPCNet: Dual Path Multi-Excitation Collaborative Network for Facial Expression Representation Learning in Videos
To obtain consistent prediction probabilities from the dual path, we further propose a dual path regularization loss, aiming to minimize the divergence between the distributions of two-path embeddings.
Ranked #13 on
Dynamic Facial Expression Recognition
on DFEW
Dynamic Facial Expression Recognition
Representation Learning
FERV39k: A Large-Scale Multi-Scene Dataset for Facial Expression Recognition in Videos
Current benchmarks for facial expression recognition (FER) mainly focus on static images, while there are limited datasets for FER in videos.
Attribute Surrogates Learning and Spectral Tokens Pooling in Transformers for Few-shot Learning
To improve data efficiency, we propose hierarchically cascaded transformers that exploit intrinsic image structures through spectral tokens pooling and optimize the learnable parameters through latent attribute surrogates.
Ranked #1 on
Few-Shot Learning
on Mini-ImageNet - 1-Shot Learning
GraphFPN: Graph Feature Pyramid Network for Object Detection
State-of-the-art methods for multi-scale feature learning focus on performing feature interactions across space and scales using neural networks with a fixed topology.
Multi-scale Matching Networks for Semantic Correspondence
We follow the coarse-to-fine matching strategy and build a top-down feature and matching enhancement scheme that is coupled with the multi-scale hierarchy of deep convolutional neural networks.
Ranked #11 on
Semantic correspondence
on SPair-71k
Label-PEnet: Sequential Label Propagation and Enhancement Networks for Weakly Supervised Instance Segmentation
Weakly-supervised instance segmentation aims to detect and segment object instances precisely, given imagelevel labels only.
Ranked #9 on
Image-level Supervised Instance Segmentation
on PASCAL VOC 2012 val
(using extra training data)
General Classification
Image-level Supervised Instance Segmentation
+6
Weakly Supervised Complementary Parts Models for Fine-Grained Image Classification from the Bottom Up
We build complementary parts models in a weakly supervised manner to retrieve information suppressed by dominant object parts detected by convolutional neural networks.
Ranked #21 on
Fine-Grained Image Classification
on CUB-200-2011
Deep Metric Learning with Hierarchical Triplet Loss
(i) we construct a hierarchical class-level tree where neighboring classes are merged recursively.
Ranked #8 on
Image Retrieval
on CARS196
Image Super-Resolution via Deterministic-Stochastic Synthesis and Local Statistical Rectification
With respect to a downsampled low resolution image, we model a high resolution image as a combination of two components, a deterministic component and a stochastic component.
Multi-Evidence Filtering and Fusion for Multi-Label Classification, Object Detection and Semantic Segmentation Based on Weakly Supervised Learning
In this paper, we propose a novel weakly supervised curriculum learning pipeline for multi-label object recognition, detection and semantic segmentation.
Ranked #15 on
Weakly Supervised Object Detection
on PASCAL VOC 2007
Borrowing Treasures from the Wealthy: Deep Transfer Learning through Selective Joint Fine-tuning
In this paper, we introduce a source-target selective joint fine-tuning scheme for improving the performance of deep learning tasks with insufficient training data.
