Search Results for author:
Found 44 papers, 19 papers with code
Learning the RoPEs: Better 2D and 3D Position Encodings with STRING
We introduce STRING: Separable Translationally Invariant Position Encodings.
A Short Note on Evaluating RepNet for Temporal Repetition Counting in Videos
We discuss some consistent issues on how RepNet has been evaluated in various papers.
Ranked #2 on
Repetitive Action Counting
on UCFRep
Vision Language Models are In-Context Value Learners
Instead, GVL poses value estimation as a temporal ordering problem over shuffled video frames; this seemingly more challenging task encourages VLMs to more fully exploit their underlying semantic and temporal grounding capabilities to differentiate frames based on their perceived task progress, consequently producing significantly better value predictions.
OVR: A Dataset for Open Vocabulary Temporal Repetition Counting in Videos
The model is trained and evaluated on the OVR dataset, and its performance assessed with and without using text to specify the target class to count.
FlexCap: Describe Anything in Images in Controllable Detail
We introduce FlexCap, a vision-language model that generates region-specific descriptions of varying lengths.
RT-H: Action Hierarchies Using Language
Predicting these language motions as an intermediate step between tasks and actions forces the policy to learn the shared structure of low-level motions across seemingly disparate tasks.
ALOHA 2: An Enhanced Low-Cost Hardware for Bimanual Teleoperation
Diverse demonstration datasets have powered significant advances in robot learning, but the dexterity and scale of such data can be limited by the hardware cost, the hardware robustness, and the ease of teleoperation.
Video Language Planning
We are interested in enabling visual planning for complex long-horizon tasks in the space of generated videos and language, leveraging recent advances in large generative models pretrained on Internet-scale data.
Learning Interactive Real-World Simulators
Applications of a real-world simulator range from controllable content creation in games and movies, to training embodied agents purely in simulation that can be directly deployed in the real world.
PaLM-E: An Embodied Multimodal Language Model
Large language models excel at a wide range of complex tasks.
Ranked #2 on
Visual Question Answering (VQA)
on OK-VQA
Scaling Robot Learning with Semantically Imagined Experience
Specifically, we make use of the state of the art text-to-image diffusion models and perform aggressive data augmentation on top of our existing robotic manipulation datasets via inpainting various unseen objects for manipulation, backgrounds, and distractors with text guidance.
Robotic Skill Acquisition via Instruction Augmentation with Vision-Language Models
To accomplish this, we introduce Data-driven Instruction Augmentation for Language-conditioned control (DIAL): we utilize semi-supervised language labels leveraging the semantic understanding of CLIP to propagate knowledge onto large datasets of unlabelled demonstration data and then train language-conditioned policies on the augmented datasets.
Contrastive Value Learning: Implicit Models for Simple Offline RL
In this paper, we propose Contrastive Value Learning (CVL), which learns an implicit, multi-step model of the environment dynamics.
Interactive Language: Talking to Robots in Real Time
We present a framework for building interactive, real-time, natural language-instructable robots in the real world, and we open source related assets (dataset, environment, benchmark, and policies).
Inner Monologue: Embodied Reasoning through Planning with Language Models
We investigate a variety of sources of feedback, such as success detection, scene description, and human interaction.
Visuomotor Control in Multi-Object Scenes Using Object-Aware Representations
Our self-supervised representations are learned by observing the agent freely interacting with different parts of the environment and is queried in two different settings: (i) policy learning and (ii) object location prediction.
Improving Zero-shot Generalization in Offline Reinforcement Learning using Generalized Similarity Functions
We show that performance of online algorithms for generalization in RL can be hindered in the offline setting due to poor estimation of similarity between observations.
Implicit Behavioral Cloning
We find that across a wide range of robot policy learning scenarios, treating supervised policy learning with an implicit model generally performs better, on average, than commonly used explicit models.
XIRL: Cross-embodiment Inverse Reinforcement Learning
We investigate the visual cross-embodiment imitation setting, in which agents learn policies from videos of other agents (such as humans) demonstrating the same task, but with stark differences in their embodiments -- shape, actions, end-effector dynamics, etc.
With a Little Help from My Friends: Nearest-Neighbor Contrastive Learning of Visual Representations
On semi-supervised learning benchmarks we improve performance significantly when only 1% ImageNet labels are available, from 53. 8% to 56. 5%.
Ranked #1 on
Image Classification
on PASCAL VOC 2007
Offline Reinforcement Learning with Fisher Divergence Critic Regularization
Many modern approaches to offline Reinforcement Learning (RL) utilize behavior regularization, typically augmenting a model-free actor critic algorithm with a penalty measuring divergence of the policy from the offline data.
Learning to Rearrange Deformable Cables, Fabrics, and Bags with Goal-Conditioned Transporter Networks
Goals cannot be as easily specified as rigid object poses, and may involve complex relative spatial relations such as "place the item inside the bag".
ADAIL: Adaptive Adversarial Imitation Learning
We present the ADaptive Adversarial Imitation Learning (ADAIL) algorithm for learning adaptive policies that can be transferred between environments of varying dynamics, by imitating a small number of demonstrations collected from a single source domain.
Counting Out Time: Class Agnostic Video Repetition Counting in the Wild
We present an approach for estimating the period with which an action is repeated in a video.
Ranked #1 on
Repetitive Action Counting
on Countix
An Analysis of Object Representations in Deep Visual Trackers
Despite these strong priors, we show that deep trackers often default to tracking by saliency detection - without relying on the object instance representation.
Imitation Learning via Off-Policy Distribution Matching
In this work, we show how the original distribution ratio estimation objective may be transformed in a principled manner to yield a completely off-policy objective.
Adaptive Adversarial Imitation Learning
We present the ADaptive Adversarial Imitation Learning (ADAIL) algorithm for learning adaptive policies that can be transferred between environments of varying dynamics, by imitating a small number of demonstrations collected from a single source domain.
Inducing Stronger Object Representations in Deep Visual Trackers
Fully convolutional deep correlation networks are integral components of state-of- the-art approaches to single object visual tracking.
Beyond Photo Realism for Domain Adaptation from Synthetic Data
As synthetic imagery is used more frequently in training deep models, it is important to understand how different synthesis techniques impact the performance of such models.
Temporal Cycle-Consistency Learning
We introduce a self-supervised representation learning method based on the task of temporal alignment between videos.
Ranked #1 on
Video Alignment
on UPenn Action
Learning Latent Plans from Play
Learning from play (LfP) offers three main advantages: 1) It is cheap.
Robotics
Discriminator-Actor-Critic: Addressing Sample Inefficiency and Reward Bias in Adversarial Imitation Learning
We identify two issues with the family of algorithms based on the Adversarial Imitation Learning framework.
Learning Actionable Representations from Visual Observations
In this work we explore a new approach for robots to teach themselves about the world simply by observing it.
Discovery of Latent 3D Keypoints via End-to-end Geometric Reasoning
We demonstrate this framework on 3D pose estimation by proposing a differentiable objective that seeks the optimal set of keypoints for recovering the relative pose between two views of an object.
PersonLab: Person Pose Estimation and Instance Segmentation with a Bottom-Up, Part-Based, Geometric Embedding Model
We present a box-free bottom-up approach for the tasks of pose estimation and instance segmentation of people in multi-person images using an efficient single-shot model.
Ranked #8 on
Multi-Person Pose Estimation
on COCO test-dev
Towards Accurate Multi-person Pose Estimation in the Wild
Trained on COCO data alone, our final system achieves average precision of 0. 649 on the COCO test-dev set and the 0. 643 test-standard sets, outperforming the winner of the 2016 COCO keypoints challenge and other recent state-of-art.
Ranked #6 on
Keypoint Detection
on COCO test-challenge
Accelerating Eulerian Fluid Simulation With Convolutional Networks
Efficient simulation of the Navier-Stokes equations for fluid flow is a long standing problem in applied mathematics, for which state-of-the-art methods require large compute resources.
Efficient ConvNet-Based Marker-Less Motion Capture in General Scenes With a Low Number of Cameras
Our approach unites a discriminative image-based joint detection method with a model-based generative motion tracking algorithm through a combined pose optimization energy.
Unsupervised Feature Learning from Temporal Data
Current state-of-the-art classification and detection algorithms rely on supervised training.
Unsupervised Learning of Spatiotemporally Coherent Metrics
Current state-of-the-art classification and detection algorithms rely on supervised training.
Efficient Object Localization Using Convolutional Networks
Recent state-of-the-art performance on human-body pose estimation has been achieved with Deep Convolutional Networks (ConvNets).
Ranked #42 on
Pose Estimation
on MPII Human Pose
MoDeep: A Deep Learning Framework Using Motion Features for Human Pose Estimation
In this work, we propose a novel and efficient method for articulated human pose estimation in videos using a convolutional network architecture, which incorporates both color and motion features.
Joint Training of a Convolutional Network and a Graphical Model for Human Pose Estimation
This paper proposes a new hybrid architecture that consists of a deep Convolutional Network and a Markov Random Field.
Learning Human Pose Estimation Features with Convolutional Networks
This paper introduces a new architecture for human pose estimation using a multi- layer convolutional network architecture and a modified learning technique that learns low-level features and higher-level weak spatial models.
