Search Results for author:
Found 34 papers, 18 papers with code
GLOV: Guided Large Language Models as Implicit Optimizers for Vision Language Models
In each respective optimization step, the ranked prompts are fed as in-context examples (with their accuracies) to equip the LLM with the knowledge of the type of text prompts preferred by the downstream VLM.
Efficient Motion Prediction: A Lightweight & Accurate Trajectory Prediction Model With Fast Training and Inference Speed
For efficient and safe autonomous driving, it is essential that autonomous vehicles can predict the motion of other traffic agents.
Vision-Language Guidance for LiDAR-based Unsupervised 3D Object Detection
To overcome these limitations, we propose a vision-language-guided unsupervised 3D detection approach that operates exclusively on LiDAR point clouds.
Into the Fog: Evaluating Multiple Object Tracking Robustness
To address these limitations, we propose a pipeline for physic-based volumetric fog simulation in arbitrary real-world MOT dataset utilizing frame-by-frame monocular depth estimation and a fog formation optical model.
MULDE: Multiscale Log-Density Estimation via Denoising Score Matching for Video Anomaly Detection
We propose a novel approach to video anomaly detection: we treat feature vectors extracted from videos as realizations of a random variable with a fixed distribution and model this distribution with a neural network.
Ranked #1 on
Anomaly Detection
on CUHK Avenue
Meta-Prompting for Automating Zero-shot Visual Recognition with LLMs
Prompt ensembling of Large Language Model (LLM) generated category-specific prompts has emerged as an effective method to enhance zero-shot recognition ability of Vision-Language Models (VLMs).
Robust Localization of Key Fob Using Channel Impulse Response of Ultra Wide Band Sensors for Keyless Entry Systems
Using neural networks for localization of key fob within and surrounding a car as a security feature for keyless entry is fast emerging.
GACE: Geometry Aware Confidence Enhancement for Black-Box 3D Object Detectors on LiDAR-Data
Widely-used LiDAR-based 3D object detectors often neglect fundamental geometric information readily available from the object proposals in their confidence estimation.
TAP: Targeted Prompting for Task Adaptive Generation of Textual Training Instances for Visual Classification
Vision and Language Models (VLMs), such as CLIP, have enabled visual recognition of a potentially unlimited set of categories described by text prompts.
Sit Back and Relax: Learning to Drive Incrementally in All Weather Conditions
We propose to store these affine parameters as a memory bank for each weather condition and plug-in their weather-specific parameters during driving (i. e. test time) when the respective weather conditions are encountered.
MAtch, eXpand and Improve: Unsupervised Finetuning for Zero-Shot Action Recognition with Language Knowledge
We adapt a VL model for zero-shot and few-shot action recognition using a collection of unlabeled videos and an unpaired action dictionary.
Ranked #3 on
Zero-Shot Action Recognition
on Charades
TAEC: Unsupervised Action Segmentation with Temporal-Aware Embedding and Clustering
Temporal action segmentation in untrimmed videos has gained increased attention recently.
MAELi: Masked Autoencoder for Large-Scale LiDAR Point Clouds
The sensing process of large-scale LiDAR point clouds inevitably causes large blind spots, i. e. regions not visible to the sensor.
Sparse Message Passing Network with Feature Integration for Online Multiple Object Tracking
Existing Multiple Object Tracking (MOT) methods design complex architectures for better tracking performance.
Video Test-Time Adaptation for Action Recognition
Our proposed method demonstrates a substantial performance gain over existing test-time adaptation approaches in both evaluations of a single distribution shift and the challenging case of random distribution shifts.
ActMAD: Activation Matching to Align Distributions for Test-Time-Training
Test-Time-Training (TTT) is an approach to cope with out-of-distribution (OOD) data by adapting a trained model to distribution shifts occurring at test-time.
MATE: Masked Autoencoders are Online 3D Test-Time Learners
Our MATE is the first Test-Time-Training (TTT) method designed for 3D data, which makes deep networks trained for point cloud classification robust to distribution shifts occurring in test data.
Test-time adversarial detection and robustness for localizing humans using ultra wide band channel impulse responses
Keyless entry systems in cars are adopting neural networks for localizing its operators.
SAILOR: Scaling Anchors via Insights into Latent Object Representation
State-of-the-art unsupervised domain adaptation approaches outsource methods to overcome the object size bias.
An Efficient Domain-Incremental Learning Approach to Drive in All Weather Conditions
This catastrophic forgetting is typically addressed via incremental learning approaches which usually re-train the model by either keeping a memory bank of training samples or keeping a copy of the entire model or model parameters for each scenario.
OccAM's Laser: Occlusion-based Attribution Maps for 3D Object Detectors on LiDAR Data
These maps indicate the importance of each 3D point in predicting the specific objects.
CycDA: Unsupervised Cycle Domain Adaptation from Image to Video
To address these challenges, we propose Cycle Domain Adaptation (CycDA), a cycle-based approach for unsupervised image-to-video domain adaptation by leveraging the joint spatial information in images and videos on the one hand and, on the other hand, training an independent spatio-temporal model to bridge the modality gap.
3D Human Pose Estimation Using Möbius Graph Convolutional Networks
In particular, this allows us to directly and explicitly encode the transformation between joints, resulting in a significantly more compact representation.
Ranked #65 on
3D Human Pose Estimation
on Human3.6M
The Norm Must Go On: Dynamic Unsupervised Domain Adaptation by Normalization
This can be a hurdle in fields which require continuous dynamic adaptation or suffer from scarcity of data, e. g. autonomous driving in challenging weather conditions.
FAST3D: Flow-Aware Self-Training for 3D Object Detectors
In the field of autonomous driving, self-training is widely applied to mitigate distribution shifts in LiDAR-based 3D object detectors.
FuseSeg: LiDAR Point Cloud Segmentation Fusing Multi-Modal Data
We introduce a simple yet effective fusion method of LiDAR and RGB data to segment LiDAR point clouds.
Deep 2.5D Vehicle Classification with Sparse SfM Depth Prior for Automated Toll Systems
Furthermore due to the design of the network, at test time only the 2D camera images are required for classification which enables the usage in portable computer vision systems.
Deep Metric Learning with BIER: Boosting Independent Embeddings Robustly
To this end, we divide the last embedding layer of a deep network into an embedding ensemble and formulate training this ensemble as an online gradient boosting problem.
Ranked #13 on
Image Retrieval
on SOP
BIER - Boosting Independent Embeddings Robustly
Learning similarity functions between image pairs with deep neural networks yields highly correlated activations of large embeddings.
Grid Loss: Detecting Occluded Faces
Detection of partially occluded objects is a challenging computer vision problem.
Encoding Based Saliency Detection for Videos and Images
We present a novel video saliency detection method to support human activity recognition and weakly supervised training of activity detection algorithms.
In Defense of Color-Based Model-Free Tracking
We evaluate our approach on recent online tracking benchmark datasets demonstrating state-of-the-art results.
Occlusion Geodesics for Online Multi-Object Tracking
Robust multi-object tracking-by-detection requires the correct assignment of noisy detection results to object trajectories.
Robust Real-Time Tracking of Multiple Objects by Volumetric Mass Densities
Combining foreground images from multiple views by projecting them onto a common ground-plane has been recently applied within many multi-object tracking approaches.
