Search Results for author:
Found 16 papers, 7 papers with code
3D-MiniNet: Learning a 2D Representation from Point Clouds for Fast and Efficient 3D LIDAR Semantic Segmentation
Fast and efficient semantic segmentation methods are needed to match the strong computational and temporal restrictions of many of these real-world applications.
Ranked #1 on
Real-Time 3D Semantic Segmentation
on SemanticKITTI
Robust and Efficient Post-Processing for Video Object Detection (REPP)
Object recognition in video is an important task for plenty of applications, including autonomous driving perception, surveillance tasks, wearable devices or IoT networks.
Ranked #17 on
Video Object Detection
on ImageNet VID
Robust and efficient post-processing for video object detection
Object recognition in video is an important task for plenty of applications, including autonomous driving perception, surveillance tasks, wearable devices or IoT networks.
Semi-Supervised Semantic Segmentation with Pixel-Level Contrastive Learning from a Class-wise Memory Bank
In an end-to-end training, the features from both labeled and unlabeled data are optimized to be similar to same-class samples from the memory bank.
Event Transformer. A sparse-aware solution for efficient event data processing
Event cameras are sensors of great interest for many applications that run in low-resource and challenging environments.
One-shot action recognition in challenging therapy scenarios
We also develop a set of complementary steps that boost the action recognition performance in the most challenging scenarios.
Ranked #4 on
One-Shot 3D Action Recognition
on NTU RGB+D 120
Domain and View-point Agnostic Hand Action Recognition
And, more importantly, when performing hand action recognition for action domains and camera perspectives which our approach has not been trained for (cross-domain action classification), our proposed framework achieves comparable performance to intra-domain state-of-the-art methods.
EV-SegNet: Semantic Segmentation for Event-based Cameras
Since there is no existing labeled dataset for this task, we propose how to automatically generate approximated semantic segmentation labels for some sequences of the DDD17 dataset, which we publish together with the model, and demonstrate they are valid to train a model for DVS data only.
Ranked #7 on
Semantic Segmentation
on DSEC
Domain Adaptation in LiDAR Semantic Segmentation by Aligning Class Distributions
Besides, we propose a learning-based approach that aligns the distribution of the semantic classes of the target domain to the source domain.
Distributed Multi-Target Tracking in Camera Networks
On the other hand, data association and information fusion are more challenging than in a centralized setup, mostly due to the lack of global and complete information.
Event Transformer+. A multi-purpose solution for efficient event data processing
Event cameras record sparse illumination changes with high temporal resolution and high dynamic range.
CLIPSwarm: Generating Drone Shows from Text Prompts with Vision-Language Models
A formation is visually represented through alpha-shape contours and the most representative color is automatically found for the input word.
SpectralWaste Dataset: Multimodal Data for Waste Sorting Automation
The increase in non-biodegradable waste is a worldwide concern.
EventSleep: Sleep Activity Recognition with Event Cameras
Our novel pipeline is able to achieve high accuracy under these challenging conditions and incorporates a Bayesian approach (Laplace ensembles) to increase the robustness in the predictions, which is fundamental for medical applications.
Active Exploration in Bayesian Model-based Reinforcement Learning for Robot Manipulation
Model-based RL, by building a dynamic model of the robot, enables data reuse and transfer learning between tasks with the same robot and similar environment.
