Search Results for author:
Found 27 papers, 17 papers with code
Optimizing Small Language Models for In-Vehicle Function-Calling
Our results demonstrate the potential of SLMs to transform vehicle control systems, enabling more intuitive interactions between users and their vehicles for an enhanced driving experience.
Muscles in Time: Learning to Understand Human Motion by Simulating Muscle Activations
In this work, we address this issue by establishing Muscles in Time (MinT), a large-scale synthetic muscle activation dataset.
Advancing Open-Set Domain Generalization Using Evidential Bi-Level Hardest Domain Scheduler
In this paper, we observe that an adaptive domain scheduler benefits more in OSDG compared with prefixed sequential and random domain schedulers.
Spacewalker: Traversing Representation Spaces for Fast Interactive Exploration and Annotation of Unstructured Data
In industries such as healthcare, finance, and manufacturing, analysis of unstructured textual data presents significant challenges for analysis and decision making.
Referring Atomic Video Action Recognition
Since these existing methods underperform on RAVAR, we introduce RefAtomNet -- a novel cross-stream attention-driven method specialized for the unique challenges of RAVAR: the need to interpret a textual referring expression for the targeted individual, utilize this reference to guide the spatial localization and harvest the prediction of the atomic actions for the referring person.
Improving Single Domain-Generalized Object Detection: A Focus on Diversification and Alignment
The results consistently demonstrate the superiority of our approach compared to existing methods.
AltChart: Enhancing VLM-based Chart Summarization Through Multi-Pretext Tasks
Chart summarization is a crucial task for blind and visually impaired individuals as it is their primary means of accessing and interpreting graphical data.
Position: Quo Vadis, Unsupervised Time Series Anomaly Detection?
The current state of machine learning scholarship in Timeseries Anomaly Detection (TAD) is plagued by the persistent use of flawed evaluation metrics, inconsistent benchmarking practices, and a lack of proper justification for the choices made in novel deep learning-based model designs.
Fourier Prompt Tuning for Modality-Incomplete Scene Segmentation
Integrating information from multiple modalities enhances the robustness of scene perception systems in autonomous vehicles, providing a more comprehensive and reliable sensory framework.
Navigating Open Set Scenarios for Skeleton-based Action Recognition
In real-world scenarios, human actions often fall outside the distribution of training data, making it crucial for models to recognize known actions and reject unknown ones.
Domain Adaptive Object Detection via Balancing Between Self-Training and Adversarial Learning
Deep learning based object detectors struggle generalizing to a new target domain bearing significant variations in object and background.
Exploring Few-Shot Adaptation for Activity Recognition on Diverse Domains
In this work, we focus on Few-Shot Domain Adaptation for Activity Recognition (FSDA-AR), which leverages a very small amount of labeled target videos to achieve effective adaptation.
Towards Activated Muscle Group Estimation in the Wild
To this intent, we provide the MuscleMap dataset featuring >15K video clips with 135 different activities and 20 labeled muscle groups.
Towards Improving Calibration in Object Detection Under Domain Shift
To this end, we first propose a new, plug-and-play, train-time calibration loss for object detection (coined as TCD).
Breaking with Fixed Set Pathology Recognition through Report-Guided Contrastive Training
We show that despite using unstructured medical report supervision, we perform on par with direct label supervision through a sophisticated inference setting.
Ranked #2 on
Thoracic Disease Classification
on ChestX-ray14
Hierarchical Nearest Neighbor Graph Embedding for Efficient Dimensionality Reduction
Dimensionality reduction is crucial both for visualization and preprocessing high dimensional data for machine learning.
Ranked #3 on
Data Augmentation
on GA1457
Synergizing between Self-Training and Adversarial Learning for Domain Adaptive Object Detection
In this paper, we propose to leverage model predictive uncertainty to strike the right balance between adversarial feature alignment and class-level alignment.
Temporally-Weighted Hierarchical Clustering for Unsupervised Action Segmentation
Action segmentation refers to inferring boundaries of semantically consistent visual concepts in videos and is an important requirement for many video understanding tasks.
Ranked #1 on
Action Segmentation
on MPII Cooking 2 Dataset
Anchor-free Small-scale Multispectral Pedestrian Detection
In this way, we can both simplify the network architecture and achieve higher detection performance, especially for pedestrians under occlusion or at low object resolution.
Clustering based Contrastive Learning for Improving Face Representations
We demonstrate our method on the challenging task of learning representations for video face clustering.
Content and Colour Distillation for Learning Image Translations with the Spatial Profile Loss
In this paper, we propose a novel method of computing the loss directly between the source and target images that enable proper distillation of shape/content and colour/style.
Self-Supervised Learning of Face Representations for Video Face Clustering
In this paper, we address video face clustering using unsupervised methods.
Efficient Parameter-free Clustering Using First Neighbor Relations
We present a new clustering method in the form of a single clustering equation that is able to directly discover groupings in the data.
A Pose-Sensitive Embedding for Person Re-Identification with Expanded Cross Neighborhood Re-Ranking
In contrast to the recent direction of explicitly modeling body parts or correcting for misalignment based on these, we show that a rather straightforward inclusion of acquired camera view and/or the detected joint locations into a convolutional neural network helps to learn a very effective representation.
Ranked #17 on
Person Re-Identification
on MARS
Deep View-Sensitive Pedestrian Attribute Inference in an end-to-end Model
The visual cues hinting at attributes can be strongly localized and inference of person attributes such as hair, backpack, shorts, etc., are highly dependent on the acquired view of the pedestrian.
Deep Perceptual Mapping for Cross-Modal Face Recognition
Our method bridges the drop in performance due to the modality gap by more than 40\%.
Ranked #2 on
Face Recognition
on UND-X1
Deep Perceptual Mapping for Thermal to Visible Face Recognition
Cross modal face matching between the thermal and visible spectrum is a much de- sired capability for night-time surveillance and security applications.
