Search Results for author:
Found 16 papers, 10 papers with code
Locating and Editing Factual Associations in GPT
To test our hypothesis that these computations correspond to factual association recall, we modify feed-forward weights to update specific factual associations using Rank-One Model Editing (ROME).
Temporal Relational Reasoning in Videos
Temporal relational reasoning, the ability to link meaningful transformations of objects or entities over time, is a fundamental property of intelligent species.
Ranked #2 on
Hand Gesture Recognition
on Jester test
Mass-Editing Memory in a Transformer
Recent work has shown exciting promise in updating large language models with new memories, so as to replace obsolete information or add specialized knowledge.
Moments in Time Dataset: one million videos for event understanding
We present the Moments in Time Dataset, a large-scale human-annotated collection of one million short videos corresponding to dynamic events unfolding within three seconds.
Multi-Moments in Time: Learning and Interpreting Models for Multi-Action Video Understanding
Videos capture events that typically contain multiple sequential, and simultaneous, actions even in the span of only a few seconds.
Cross-view Semantic Segmentation for Sensing Surroundings
Our further experiment on a LoCoBot robot shows that our model enables the surrounding sensing capability from 2D image input.
GANalyze: Toward Visual Definitions of Cognitive Image Properties
We introduce a framework that uses Generative Adversarial Networks (GANs) to study cognitive properties like memorability, aesthetics, and emotional valence.
Unsupervised Learning from Video with Deep Neural Embeddings
Because of the rich dynamical structure of videos and their ubiquity in everyday life, it is a natural idea that video data could serve as a powerful unsupervised learning signal for training visual representations in deep neural networks.
Contrastive Feature Loss for Image Prediction
Training supervised image synthesis models requires a critic to compare two images: the ground truth to the result.
We Have So Much In Common: Modeling Semantic Relational Set Abstractions in Videos
This allows our model to perform cognitive tasks such as set abstraction (which general concept is in common among a set of videos?
The Algonauts Project: A Platform for Communication between the Sciences of Biological and Artificial Intelligence
Recently, researchers of natural intelligence have begun using those AI models to explore how the brain performs such tasks.
VA-RED$^2$: Video Adaptive Redundancy Reduction
An inherent property of real-world videos is the high correlation of information across frames which can translate into redundancy in either temporal or spatial feature maps of the models, or both.
Robust Cross-Modal Representation Learning with Progressive Self-Distillation
The learning objective of vision-language approach of CLIP does not effectively account for the noisy many-to-many correspondences found in web-harvested image captioning datasets, which contributes to its compute and data inefficiency.
Ranked #98 on
Image Classification
on ObjectNet
(using extra training data)
Deepfake Caricatures: Amplifying attention to artifacts increases deepfake detection by humans and machines
Second, they allow us to generate novel "Deepfake Caricatures": transformations of the deepfake that exacerbate artifacts to improve human detection.
Three ways to improve feature alignment for open vocabulary detection
The core problem in zero-shot open vocabulary detection is how to align visual and text features, so that the detector performs well on unseen classes.
