Search Results for author:
Found 34 papers, 16 papers with code
CinePile: A Long Video Question Answering Dataset and Benchmark
Current datasets for long-form video understanding often fall short of providing genuine long-form comprehension challenges, as many tasks derived from these datasets can be successfully tackled by analyzing just one or a few random frames from a video.
GaNI: Global and Near Field Illumination Aware Neural Inverse Rendering
In this paper, we present GaNI, a Global and Near-field Illumination-aware neural inverse rendering technique that can reconstruct geometry, albedo, and roughness parameters from images of a scene captured with co-located light and camera.
Measured Albedo in the Wild: Filling the Gap in Intrinsics Evaluation
We then finetune different algorithms on our MAW dataset to significantly improve the quality of the reconstructed albedo both quantitatively and qualitatively.
Preserve Your Own Correlation: A Noise Prior for Video Diffusion Models
Despite tremendous progress in generating high-quality images using diffusion models, synthesizing a sequence of animated frames that are both photorealistic and temporally coherent is still in its infancy.
Ranked #8 on
Text-to-Video Generation
on UCF-101
HaLP: Hallucinating Latent Positives for Skeleton-based Self-Supervised Learning of Actions
In this work, we propose a new contrastive learning approach to train models for skeleton-based action recognition without labels.
LD-ZNet: A Latent Diffusion Approach for Text-Based Image Segmentation
First, we show that the latent space of LDMs (z-space) is a better input representation compared to other feature representations like RGB images or CLIP encodings for text-based image segmentation.
Hyperbolic Contrastive Learning for Visual Representations beyond Objects
To exploit such a structure, we propose a contrastive learning framework where a Euclidean loss is used to learn object representations and a hyperbolic loss is used to encourage representations of scenes to lie close to representations of their constituent objects in a hyperbolic space.
A simple, efficient and scalable contrastive masked autoencoder for learning visual representations
Our framework is a minimal and conceptually clean synthesis of (C) contrastive learning, (A) masked autoencoders, and (N) the noise prediction approach used in diffusion models.
Poisons that are learned faster are more effective
We advocate for evaluating poisons in terms of peak test accuracy.
Long Video Generation with Time-Agnostic VQGAN and Time-Sensitive Transformer
Videos are created to express emotion, exchange information, and share experiences.
Ranked #21 on
Video Generation
on UCF-101
On the Spectral Bias of Convolutional Neural Tangent and Gaussian Process Kernels
We study the properties of various over-parametrized convolutional neural architectures through their respective Gaussian process and neural tangent kernels.
Object-Aware Cropping for Self-Supervised Learning
This assumption is mostly satisfied in datasets such as ImageNet where there is a large, centered object, which is highly likely to be present in random crops of the full image.
Robust Contrastive Learning Using Negative Samples with Diminished Semantics
We also show that model bias favors texture and shape features differently under different test settings.
Maneuver Identification Challenge
The Maneuver Identification Challenge hosted at maneuver-id. mit. edu provides thousands of trajectories collected from pilots practicing in flight simulators, descriptions of maneuvers, and examples of these maneuvers performed by experienced pilots.
Improved Detection of Face Presentation Attacks Using Image Decomposition
Presentation attack detection (PAD) is a critical component in secure face authentication.
Shift Invariance Can Reduce Adversarial Robustness
Using this, we prove that shift invariance in neural networks produces adversarial examples for the simple case of two classes, each consisting of a single image with a black or white dot on a gray background.
Low Curvature Activations Reduce Overfitting in Adversarial Training
In particular, we show that using activation functions with low (exact or approximate) curvature values has a regularization effect that significantly reduces both the standard and robust generalization gaps in adversarial training.
Learning Visual Representations for Transfer Learning by Suppressing Texture
Recent literature has shown that features obtained from supervised training of CNNs may over-emphasize texture rather than encoding high-level information.
Ranked #19 on
Object Detection
on PASCAL VOC 2007
On the Similarity between the Laplace and Neural Tangent Kernels
Experiments show that these kernel methods perform similarly to real neural networks.
SharinGAN: Combining Synthetic and Real Data for Unsupervised Geometry Estimation
Ideally, this results in images from two domains that present shared information to the primary network.
Ranked #3 on
Monocular Depth Estimation
on Make3D
Towards Automatic Generation of Questions from Long Answers
Therefore, we propose a novel evaluation benchmark to assess the performance of existing AQG systems for long-text answers.
Frequency Bias in Neural Networks for Input of Non-Uniform Density
Recent works have partly attributed the generalization ability of over-parameterized neural networks to frequency bias -- networks trained with gradient descent on data drawn from a uniform distribution find a low frequency fit before high frequency ones.
The Convergence Rate of Neural Networks for Learned Functions of Different Frequencies
We study the relationship between the frequency of a function and the speed at which a neural network learns it.
Adversarially robust transfer learning
By training classifiers on top of these feature extractors, we produce new models that inherit the robustness of their parent networks.
Understanding the (un)interpretability of natural image distributions using generative models
Probability density estimation is a classical and well studied problem, but standard density estimation methods have historically lacked the power to model complex and high-dimensional image distributions.
SfSNet: Learning Shape, Reflectance and Illuminance of Faces in the Wild
SfSNet learns from a mixture of labeled synthetic and unlabeled real world images.
Stabilizing Adversarial Nets With Prediction Methods
Adversarial neural networks solve many important problems in data science, but are notoriously difficult to train.
3D Menagerie: Modeling the 3D shape and pose of animals
The best human body models are learned from thousands of 3D scans of people in specific poses, which is infeasible with live animals.
Big Batch SGD: Automated Inference using Adaptive Batch Sizes
The high fidelity gradients enable automated learning rate selection and do not require stepsize decay.
Biconvex Relaxation for Semidefinite Programming in Computer Vision
We propose a general framework to approximately solve large-scale semidefinite problems (SDPs) at low complexity.
Efficient Representation of Low-Dimensional Manifolds using Deep Networks
We consider the ability of deep neural networks to represent data that lies near a low-dimensional manifold in a high-dimensional space.
A Hyperelastic Two-Scale Optimization Model for Shape Matching
We suggest a novel shape matching algorithm for three-dimensional surface meshes of disk or sphere topology.
Locally Scale-Invariant Convolutional Neural Networks
We show on a modified MNIST dataset that when faced with scale variation, building in scale-invariance allows ConvNets to learn more discriminative features with reduced chances of over-fitting.
Comparing apples to apples in the evaluation of binary coding methods
We discuss methodological issues related to the evaluation of unsupervised binary code construction methods for nearest neighbor search.
