Search Results for author:
Found 9 papers, 2 papers with code
DAS: A Deformable Attention to Capture Salient Information in CNNs
Our claim is that DAS's ability to pay increased attention to relevant features results in performance improvements when added to popular CNNs for Image Classification and Object Detection.
Ranked #1 on
Object Detection
on MSCOCO
DragD3D: Vertex-based Editing for Realistic Mesh Deformations using 2D Diffusion Priors
Direct mesh editing and deformation are key components in the geometric modeling and animation pipeline.
Simulated Annealing in Early Layers Leads to Better Generalization
Our principal innovation in this work is to use Simulated annealing in EArly Layers (SEAL) of the network in place of re-initialization of later layers.
Prototype-Sample Relation Distillation: Towards Replay-Free Continual Learning
Class prototypes are evolved continually in the same latent space, enabling learning and prediction at any point.
Probing Representation Forgetting in Supervised and Unsupervised Continual Learning
Continual Learning research typically focuses on tackling the phenomenon of catastrophic forgetting in neural networks.
Tackling Online One-Class Incremental Learning by Removing Negative Contrasts
Recent work studies the supervised online continual learning setting where a learner receives a stream of data whose class distribution changes over time.
Toward Multimodal Interaction in Scalable Visual Digital Evidence Visualization Using Computer Vision Techniques and ISS
Visualization requirements in Forensic Lucid have to do with different levels of case knowledge abstraction, representation, aggregation, as well as the operational aspects as the final long-term goal of this proposal.
CAMREP- Concordia Action and Motion Repository
Action recognition, motion classification, gait analysis and synthesis are fundamental problems in a number of fields such as computer graphics, bio-mechanics and human computer interaction that generate a large body of research.
Multi-label Pixelwise Classification for Reconstruction of Large-scale Urban Areas
In fact, for single-label object classification [i. e. only one object present in the image] the state-of-the-art techniques employ deep neural networks and are reporting very close to human-like performance.
