Search Results for author:
Found 32 papers, 22 papers with code
VAU-R1: Advancing Video Anomaly Understanding via Reinforcement Fine-Tuning
Video Anomaly Understanding (VAU) is essential for applications such as smart cities, security surveillance, and disaster alert systems, yet remains challenging due to its demand for fine-grained spatio-temporal perception and robust reasoning under ambiguity.
Debiased Opto-electronic Joint Transform Correlator for Enhanced Real-Time Pattern Recognition
Opto-electronic joint transform correlators (OJTCs) use a focal plane array (FPA) to detect the joint power spectrum (JPS) of two input images, projecting it onto a spatial light modulator (SLM) to be optically Fourier transformed.
Shift, Scale and Rotation Invariant Multiple Object Detection using Balanced Joint Transform Correlator
The Polar Mellin Transform (PMT) is a well-known technique that converts images into shift, scale and rotation invariant signatures for object detection using opto-electronic correlators.
SimROD: A Simple Baseline for Raw Object Detection with Global and Local Enhancements
Most visual models are designed for sRGB images, yet RAW data offers significant advantages for object detection by preserving sensor information before ISP processing.
DEIM: DETR with Improved Matching for Fast Convergence
We introduce DEIM, an innovative and efficient training framework designed to accelerate convergence in real-time object detection with Transformer-based architectures (DETR).
ForgeryTTT: Zero-Shot Image Manipulation Localization with Test-Time Training
During test-time training, the predicted mask from the localization head is used for the classification head to update the image encoder for better adaptation.
HTR-VT: Handwritten Text Recognition with Vision Transformer
To address this limitation, we introduce a data-efficient ViT method that uses only the encoder of the standard transformer.
Ranked #1 on
Handwritten Text Recognition
on LAM(line-level)
From COCO to COCO-FP: A Deep Dive into Background False Positives for COCO Detectors
In this study, we introduce COCO-FP, a new evaluation dataset derived from the ImageNet-1K dataset, designed to address this issue.
Technique Report of CVPR 2024 PBDL Challenges
The intersection of physics-based vision and deep learning presents an exciting frontier for advancing computer vision technologies.
Depth-aware Test-Time Training for Zero-shot Video Object Segmentation
In this work, we introduce a test-time training (TTT) strategy to address the problem.
SURE: SUrvey REcipes for building reliable and robust deep networks
In this paper, we revisit techniques for uncertainty estimation within deep neural networks and consolidate a suite of techniques to enhance their reliability.
Ranked #1 on
Learning with noisy labels
on ANIMAL
High-speed Opto-electronic Pre-processing of Polar Mellin Transform for Shift, Scale and Rotation Invariant Image Recognition at Record-Breaking Speeds
Space situational awareness demands efficient monitoring of terrestrial sites and celestial bodies, necessitating advanced target recognition systems.
LivelySpeaker: Towards Semantic-Aware Co-Speech Gesture Generation
While previous methods are able to generate speech rhythm-synchronized gestures, the semantic context of the speech is generally lacking in the gesticulations.
Explicit Visual Prompting for Universal Foreground Segmentations
We take inspiration from the widely-used pre-training and then prompt tuning protocols in NLP and propose a new visual prompting model, named Explicit Visual Prompting (EVP).
Ranked #3 on
Salient Object Detection
on DUT-OMRON
Explicit Visual Prompting for Low-Level Structure Segmentations
Different from the previous visual prompting which is typically a dataset-level implicit embedding, our key insight is to enforce the tunable parameters focusing on the explicit visual content from each individual image, i. e., the features from frozen patch embeddings and the input's high-frequency components.
Ranked #4 on
Salient Object Detection
on HKU-IS
T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representations
Additionally, we conduct analyses on HumanML3D and observe that the dataset size is a limitation of our approach.
Ranked #2 on
Motion Synthesis
on Motion-X
Generating Human Motion From Textual Descriptions With Discrete Representations
Additionally, we conduct analyses on HumanML3D and observe that the dataset size is a limitation of our approach.
SadTalker: Learning Realistic 3D Motion Coefficients for Stylized Audio-Driven Single Image Talking Face Animation
We present SadTalker, which generates 3D motion coefficients (head pose, expression) of the 3DMM from audio and implicitly modulates a novel 3D-aware face render for talking head generation.
TokenCut: Segmenting Objects in Images and Videos with Self-supervised Transformer and Normalized Cut
This method also achieves competitive results for unsupervised video object segmentation tasks with the DAVIS, SegTV2, and FBMS datasets.
Ranked #5 on
Unsupervised Instance Segmentation
on COCO val2017
Jigsaw-ViT: Learning Jigsaw Puzzles in Vision Transformer
In this paper, we explore solving jigsaw puzzle as a self-supervised auxiliary loss in ViT for image classification, named Jigsaw-ViT.
Ranked #1 on
Learning with noisy labels
on ANIMAL
Back to MLP: A Simple Baseline for Human Motion Prediction
This paper tackles the problem of human motion prediction, consisting in forecasting future body poses from historically observed sequences.
Compressing Features for Learning with Noisy Labels
This decomposition provides three insights: (i) it shows that over-fitting is indeed an issue for learning with noisy labels; (ii) through an information bottleneck formulation, it explains why the proposed feature compression helps in combating label noise; (iii) it gives explanations on the performance boost brought by incorporating compression regularization into Co-teaching.
Ranked #11 on
Image Classification
on Clothing1M
(using extra training data)
Self-Supervised Transformers for Unsupervised Object Discovery using Normalized Cut
For unsupervised saliency detection, we improve IoU for 4. 9%, 5. 2%, 12. 9% on ECSSD, DUTS, DUT-OMRON respectively compared to previous state of the art.
Ranked #1 on
Weakly-Supervised Object Localization
on CUB
Re-ranking for image retrieval and transductive few-shot classification
In the problems of image retrieval and few-shot classification, the mainstream approaches focus on learning a better feature representation.
Learning Co-segmentation by Segment Swapping for Retrieval and Discovery
The goal of this work is to efficiently identify visually similar patterns in images, e. g. identifying an artwork detail copied between an engraving and an oil painting, or recognizing parts of a night-time photograph visible in its daytime counterpart.
Image Collation: Matching illustrations in manuscripts
For an historian, the first step in studying their evolution in a corpus of similar manuscripts is to identify which ones correspond to each other.
Boosting Co-teaching with Compression Regularization for Label Noise
On Clothing1M, our approach obtains 74. 9% accuracy which is slightly better than that of DivideMix.
Ranked #13 on
Image Classification
on Clothing1M
(using extra training data)
Empirical Bayes Transductive Meta-Learning with Synthetic Gradients
The evidence lower bound of the marginal log-likelihood of empirical Bayes decomposes as a sum of local KL divergences between the variational posterior and the true posterior on the query set of each task.
Ranked #13 on
Few-Shot Image Classification
on CIFAR-FS 5-way (1-shot)
RANSAC-Flow: generic two-stage image alignment
Coarse alignment is performed using RANSAC on off-the-shelf deep features.
Marginalized Average Attentional Network for Weakly-Supervised Learning
The MAAN employs a novel marginalized average aggregation (MAA) module and learns a set of latent discriminative probabilities in an end-to-end fashion.
Ranked #13 on
Weakly Supervised Action Localization
on ActivityNet-1.3
(mAP@0.5 metric)
Weakly Supervised Action Localization
Weakly-supervised Learning
Discovering Visual Patterns in Art Collections with Spatially-consistent Feature Learning
Our goal in this paper is to discover near duplicate patterns in large collections of artworks.
