Search Results for author:
Found 28 papers, 5 papers with code
Interpretable Zero-shot Learning with Infinite Class Concepts
This paper redefines class semantics in ZSL with a focus on transferability and discriminability, introducing a novel framework called Zero-shot Learning with Infinite Class Concepts (InfZSL).
Is Temporal Prompting All We Need For Limited Labeled Action Recognition?
Recent advancements in visual-language models, especially based on contrastive pretraining, have shown remarkable generalization in zero-shot tasks, helping to overcome this dependence on labeled datasets.
CAPT: Class-Aware Prompt Tuning for Federated Long-Tailed Learning with Vision-Language Model
Effectively handling the co-occurrence of non-IID data and long-tailed distributions remains a critical challenge in federated learning.
Enhancing Generalization via Sharpness-Aware Trajectory Matching for Dataset Condensation
These issues deteriorate when the datasets are learned via matching the trajectories of networks trained on the real and synthetic datasets with a long horizon inner-loop.
Twin Trigger Generative Networks for Backdoor Attacks against Object Detection
Furthermore, the triggers for most existing backdoor attacks on object detection are manually generated, requiring prior knowledge and consistent patterns between the training and inference stages.
Principles of Visual Tokens for Efficient Video Understanding
First, we develop an oracle for the value of tokens which exposes a clear Pareto distribution where most tokens have remarkably low value, and just a few carry most of the perceptual information.
Continual Learning Improves Zero-Shot Action Recognition
In this paper, we propose a novel method based on continual learning to address zero-shot action recognition.
FE-Adapter: Adapting Image-based Emotion Classifiers to Videos
This breakthrough highlights the potential for cross-modality approaches in enhancing the capabilities of AI models, particularly in fields like video emotion analysis where the demand for efficiency and accuracy is constantly rising.
Ranked #7 on
Dynamic Facial Expression Recognition
on FERV39k
CC-SAM: SAM with Cross-feature Attention and Context for Ultrasound Image Segmentation
The Segment Anything Model (SAM) has achieved remarkable successes in the realm of natural image segmentation, but its deployment in the medical imaging sphere has encountered challenges.
Masks and Manuscripts: Advancing Medical Pre-training with End-to-End Masking and Narrative Structuring
Contemporary medical contrastive learning faces challenges from inconsistent semantics and sample pair morphology, leading to dispersed and converging semantic shifts.
Ranked #89 on
Multi-Label Classification
on CheXpert
Reimagining Reality: A Comprehensive Survey of Video Inpainting Techniques
This paper offers a comprehensive analysis of recent advancements in video inpainting techniques, a critical subset of computer vision and artificial intelligence.
Adversarial Augmentation Training Makes Action Recognition Models More Robust to Realistic Video Distribution Shifts
More precisely, we created dataset splits of HMDB-51 or UCF-101 for training, and Kinetics-400 for testing, using the subset of the classes that are overlapping in both train and test datasets.
Watt For What: Rethinking Deep Learning's Energy-Performance Relationship
Deep learning models have revolutionized various fields, from image recognition to natural language processing, by achieving unprecedented levels of accuracy.
Telling Stories for Common Sense Zero-Shot Action Recognition
The textual narratives forge connections between seen and unseen classes, overcoming the bottleneck of labeled data that has long impeded advancements in this exciting domain.
Bridging the Projection Gap: Overcoming Projection Bias Through Parameterized Distance Learning
Generalized zero-shot learning (GZSL) aims to recognize samples from both seen and unseen classes using only seen class samples for training.
Optimizing ViViT Training: Time and Memory Reduction for Action Recognition
In this paper, we address the challenges posed by the substantial training time and memory consumption associated with video transformers, focusing on the ViViT (Video Vision Transformer) model, in particular the Factorised Encoder version, as our baseline for action recognition tasks.
Synthetic Sample Selection for Generalized Zero-Shot Learning
Generalized Zero-Shot Learning (GZSL) has emerged as a pivotal research domain in computer vision, owing to its capability to recognize objects that have not been seen during training.
Ranked #1 on
Generalized Zero-Shot Learning
on Oxford 102 Flower
A Closer Look at Temporal Ordering in the Segmentation of Instructional Videos
We refer to this task as Procedure Segmentation and Summarization (PSS).
Learn2Augment: Learning to Composite Videos for Data Augmentation in Action Recognition
We propose to learn what makes a good video for action recognition and select only high-quality samples for augmentation.
Ranked #2 on
Few Shot Action Recognition
on HMDB51
Capturing Temporal Information in a Single Frame: Channel Sampling Strategies for Action Recognition
We address the problem of capturing temporal information for video classification in 2D networks, without increasing their computational cost.
A New Split for Evaluating True Zero-Shot Action Recognition
We benchmark several recent approaches on the proposed True Zero-Shot(TruZe) Split for UCF101 and HMDB51, with zero-shot and generalized zero-shot evaluation.
CLASTER: Clustering with Reinforcement Learning for Zero-Shot Action Recognition
Theproblem can be seen as learning a function which general-izes well to instances of unseen classes without losing dis-crimination between classes.
Ranked #2 on
Zero-Shot Action Recognition
on Olympics
SMART Frame Selection for Action Recognition
In this work, however, we focus on the more standard short, trimmed action recognition problem.
Ranked #6 on
Action Recognition
on UCF101
ALBA : Reinforcement Learning for Video Object Segmentation
We treat this as a grouping problem by exploiting object proposals and making a joint inference about grouping over both space and time.
Using an ensemble color space model to tackle adversarial examples
Minute pixel changes in an image drastically change the prediction that the deep learning model makes.
StegColNet: Steganalysis based on an ensemble colorspace approach
Image steganography refers to the process of hiding information inside images.
ColorNet: Investigating the importance of color spaces for image classification
These color images are taken as input in the form of RGB images and classification is done without modifying them.
Ranked #3 on
Image Classification
on SVHN
