Search Results for author:
Found 38 papers, 20 papers with code
n-Reference Transfer Learning for Saliency Prediction
The proposed framework is gradient-based and model-agnostic.
Finetuning Text-to-Image Diffusion Models for Fairness
The rapid adoption of text-to-image diffusion models in society underscores an urgent need to address their biases.
ELIP: Efficient Language-Image Pre-training with Fewer Vision Tokens
Learning a versatile language-image model is computationally prohibitive under a limited computing budget.
MCM: Multi-condition Motion Synthesis Framework for Multi-scenario
We also introduce a Transformer-based diffusion model MWNet (DDPM-like) as our main branch that can capture the spatial complexity and inter-joint correlations in motion sequences through a channel-dimension self-attention module.
A Study on Differentiable Logic and LLMs for EPIC-KITCHENS-100 Unsupervised Domain Adaptation Challenge for Action Recognition 2023
Our research focuses on the innovative application of a differentiable logic loss in the training to leverage the co-occurrence relations between verb and noun, as well as the pre-trained Large Language Models (LLMs) to generate the logic rules for the adaptation to unseen action labels.
Chairs Can be Stood on: Overcoming Object Bias in Human-Object Interaction Detection
To quantitatively study the object bias problem, we advocate a new protocol for evaluating model performance.
Distance Matters in Human-Object Interaction Detection
2) Insufficient number of distant interactions in benchmark datasets results in under-fitting on these instances.
A Unified End-to-End Retriever-Reader Framework for Knowledge-based VQA
On the other hand, pertaining to the implicit knowledge, the multi-modal implicit knowledge for knowledge-based VQA still remains largely unexplored.
Learning to Minimize the Remainder in Supervised Learning
To this end, we propose a new learning approach, namely gradient adjustment learning (GAL), to leverage the knowledge learned from the past training iterations to adjust vanilla gradients, such that the remainders are minimized and the approximations are improved.
Learning to Predict Gradients for Semi-Supervised Continual Learning
To explore these issues, we formulate a new semi-supervised continual learning method, which can be generically applied to existing continual learning models.
Unsupervised Motion Representation Learning with Capsule Autoencoders
We propose the Motion Capsule Autoencoder (MCAE), which addresses a key challenge in the unsupervised learning of motion representations: transformation invariance.
Learning to Predict Trustworthiness with Steep Slope Loss
Secondly, due to the data complexity, it is challenging to differentiate the incorrect predictions from the correct ones on real-world large-scale datasets.
Fair Representation: Guaranteeing Approximate Multiple Group Fairness for Unknown Tasks
Motivated by scenarios where data is used for diverse prediction tasks, we study whether fair representation can be used to guarantee fairness for unknown tasks and for multiple fairness notions simultaneously.
Relation-aware Compositional Zero-shot Learning for Attribute-Object Pair Recognition
The concept module generates semantically meaningful features for primitive concepts, whereas the visual module extracts visual features for attributes and objects from input images.
Learning Causal Representation for Training Cross-Domain Pose Estimator via Generative Interventions
In this work, we take a step towards training robust models for cross-domain pose estimation task, which brings together ideas from causal representation learning and generative adversarial networks.
$n$-Reference Transfer Learning for Saliency Prediction
The proposed framework is gradient-based and model-agnostic.
GradMix: Multi-source Transfer across Domains and Tasks
Therefore, it is important to develop algorithms that can leverage off-the-shelf labeled dataset to learn useful knowledge for the target task.
Weakly-Supervised Multi-Person Action Recognition in 360$^{\circ}$ Videos
To enable research in this direction, we introduce 360Action, the first omnidirectional video dataset for multi-person action recognition.
Direction Concentration Learning: Enhancing Congruency in Machine Learning
We propose a Direction Concentration Learning (DCL) method to improve congruency in the learning process, where enhancing congruency influences the convergence path to be less circuitous.
Ranked #8 on
Image Classification
on Tiny ImageNet Classification
(using extra training data)
Explainable Video Action Reasoning via Prior Knowledge and State Transitions
Finally, by sequentially examining each state transition in the video graph, our method can detect and explain how those actions are executed with prior knowledge, just like the logical manner of thinking by humans.
BEHAVIOR MODULE IN NEURAL NETWORKS
This property is particularly useful for user modeling (as for dialog agents) and recommendation tasks, as allows learning personalized representations of different user states.
$\mathcal{G}$-softmax: Improving Intra-class Compactness and Inter-class Separability of Features
In addition, analysis of the intra-class compactness and inter-class separability demonstrates the advantages of the proposed function over the softmax function, which is consistent with the performance improvement.
Learning to Learn from Noisy Labeled Data
Despite the success of deep neural networks (DNNs) in image classification tasks, the human-level performance relies on massive training data with high-quality manual annotations, which are expensive and time-consuming to collect.
Ranked #26 on
Image Classification
on Clothing1M
(using extra training data)
Visual Social Relationship Recognition
Social relationships form the basis of social structure of humans.
Unsupervised Online Video Object Segmentation with Motion Property Understanding
Moreover, our method achieves better performance than the best unsupervised offline algorithm on the DAVIS-2016 benchmark dataset.
Unsupervised Learning of View-invariant Action Representations
Different from previous works in video representation learning, our unsupervised learning task is to predict 3D motion in multiple target views using video representation from a source view.
Interact as You Intend: Intention-Driven Human-Object Interaction Detection
The recent advances in instance-level detection tasks lay strong foundation for genuine comprehension of the visual scenes.
Video Storytelling: Textual Summaries for Events
Video storytelling introduces new challenges, mainly due to the diversity of the story and the length and complexity of the video.
Attention Transfer from Web Images for Video Recognition
However, due to the domain shift problem, the performance of Web images trained deep classifiers tend to degrade when directly deployed to videos.
Dual-Glance Model for Deciphering Social Relationships
Since the beginning of early civilizations, social relationships derived from each individual fundamentally form the basis of social structure in our daily life.
Ranked #3 on
Visual Social Relationship Recognition
on PIPA
Multi-Camera Action Dataset for Cross-Camera Action Recognition Benchmarking
To enable the study of this problem, there exist a vast number of action datasets, which are recorded under controlled laboratory settings, real-world surveillance environments, or crawled from the Internet.
Label Consistent Quadratic Surrogate Model for Visual Saliency Prediction
In addition, since new datasets are built and shared in the community from time to time, it would be good not to retrain the entire model when new data are added.
Automatic Classification of Human Epithelial Type 2 Cell Indirect Immunofluorescence Images using Cell Pyramid Matching
This paper describes a novel system for automatic classification of images obtained from Anti-Nuclear Antibody (ANA) pathology tests on Human Epithelial type 2 (HEp-2) cells using the Indirect Immunofluorescence (IIF) protocol.
Dynamic Amelioration of Resolution Mismatches for Local Feature Based Identity Inference
While existing face recognition systems based on local features are robust to issues such as misalignment, they can exhibit accuracy degradation when comparing images of differing resolutions.
Classification of Human Epithelial Type 2 Cell Indirect Immunofluoresence Images via Codebook Based Descriptors
In this paper, we propose a cell classification system comprised of a dual-region codebook-based descriptor, combined with the Nearest Convex Hull Classifier.
Patch-based Probabilistic Image Quality Assessment for Face Selection and Improved Video-based Face Recognition
In video based face recognition, face images are typically captured over multiple frames in uncontrolled conditions, where head pose, illumination, shadowing, motion blur and focus change over the sequence.
Combined Learning of Salient Local Descriptors and Distance Metrics for Image Set Face Verification
In contrast to comparing faces via single exemplars, matching sets of face images increases robustness and discrimination performance.
On Robust Face Recognition via Sparse Encoding: the Good, the Bad, and the Ugly
Thorough experiments on AR, FERET, exYaleB, BANCA and ChokePoint datasets show that the proposed local SR approach obtains considerably better and more robust performance than several previous state-of-the-art holistic SR methods, in both verification and closed-set identification problems.
