Search Results for author:
Found 17 papers, 2 papers with code
EMMA: End-to-End Multimodal Model for Autonomous Driving
We show that co-training EMMA with planner trajectories, object detection, and road graph tasks yields improvements across all three domains, highlighting EMMA's potential as a generalist model for autonomous driving applications.
Multi-Task Dynamic Pricing in Credit Market with Contextual Information
We show that the regret of our policy is better than both the policy that treats each security individually and the policy that treats all securities as the same.
MoST: Multi-modality Scene Tokenization for Motion Prediction
This symbolic representation is a high-level abstraction of the real world, which may render the motion prediction model vulnerable to perception errors (e. g., failures in detecting open-vocabulary obstacles) while missing salient information from the scene context (e. g., poor road conditions).
3D Open-Vocabulary Panoptic Segmentation with 2D-3D Vision-Language Distillation
3D panoptic segmentation is a challenging perception task, especially in autonomous driving.
Unsupervised 3D Perception with 2D Vision-Language Distillation for Autonomous Driving
Closed-set 3D perception models trained on only a pre-defined set of object categories can be inadequate for safety critical applications such as autonomous driving where new object types can be encountered after deployment.
3D Human Keypoints Estimation From Point Clouds in the Wild Without Human Labels
We show that by training on a large training set from Waymo Open Dataset without any human annotated keypoints, we are able to achieve reasonable performance as compared to the fully supervised approach.
HUM3DIL: Semi-supervised Multi-modal 3D Human Pose Estimation for Autonomous Driving
Autonomous driving is an exciting new industry, posing important research questions.
Motion Inspired Unsupervised Perception and Prediction in Autonomous Driving
Learning-based perception and prediction modules in modern autonomous driving systems typically rely on expensive human annotation and are designed to perceive only a handful of predefined object categories.
Risk-Aware Linear Bandits: Theory and Applications in Smart Order Routing
Then, we rigorously analyze their near-optimal regret upper bounds to show that, by leveraging the linear structure, our algorithms can dramatically reduce the regret when compared to existing methods.
Home Action Genome: Cooperative Compositional Action Understanding
However, there remains a lack of studies that extend action composition and leverage multiple viewpoints and multiple modalities of data for representation learning.
Ranked #1 on
Video Classification
on Home Action Genome
Detecting Human-Object Relationships in Videos
We study a crucial problem in video analysis: human-object relationship detection.
Action Genome: Actions As Compositions of Spatio-Temporal Scene Graphs
Next, by decomposing and learning the temporal changes in visual relationships that result in an action, we demonstrate the utility of a hierarchical event decomposition by enabling few-shot action recognition, achieving 42. 7% mAP using as few as 10 examples.
Action Genome: Actions as Composition of Spatio-temporal Scene Graphs
Next, by decomposing and learning the temporal changes in visual relationships that result in an action, we demonstrate the utility of a hierarchical event decomposition by enabling few-shot action recognition, achieving 42. 7% mAP using as few as 10 examples.
Learning Temporal Action Proposals With Fewer Labels
Most current methods for training action proposal modules rely on fully supervised approaches that require large amounts of annotated temporal action intervals in long video sequences.
Ranked #3 on
Semi-Supervised Action Detection
on ActivityNet-1.3
Few-Shot Video Classification via Temporal Alignment
In this paper, we propose Temporal Alignment Module (TAM), a novel few-shot learning framework that can learn to classify a previous unseen video.
End-to-End Joint Semantic Segmentation of Actors and Actions in Video
Traditional video understanding tasks include human action recognition and actor/object semantic segmentation.
DeformNet: Free-Form Deformation Network for 3D Shape Reconstruction from a Single Image
We evaluate our approach on the ShapeNet dataset and show that - (a) the Free-Form Deformation layer is a powerful new building block for Deep Learning models that manipulate 3D data (b) DeformNet uses this FFD layer combined with shape retrieval for smooth and detail-preserving 3D reconstruction of qualitatively plausible point clouds with respect to a single query image (c) compared to other state-of-the-art 3D reconstruction methods, DeformNet quantitatively matches or outperforms their benchmarks by significant margins.
