Search Results for author:
Found 62 papers, 13 papers with code
CausalChaos! Dataset for Comprehensive Causal Action Question Answering Over Longer Causal Chains Grounded in Dynamic Visual Scenes
We will release our dataset, codes, and models to help future efforts in this domain.
Zero Shot Open-ended Video Inference
Zero-shot open-ended inference on untrimmed videos poses a significant challenge, especially when no annotated data is utilized to navigate the inference direction.
Learning to Visually Connect Actions and their Effects
We propose different CATE-based task formulations, such as action selection and action specification, where video understanding models connect actions and effects at semantic and fine-grained levels.
Motion Flow Matching for Human Motion Synthesis and Editing
In this paper, we propose \emph{Motion Flow Matching}, a novel generative model designed for human motion generation featuring efficient sampling and effectiveness in motion editing applications.
Semi-supervised multimodal coreference resolution in image narrations
In this paper, we study multimodal coreference resolution, specifically where a longer descriptive text, i. e., a narration is paired with an image.
ClipSitu: Effectively Leveraging CLIP for Conditional Predictions in Situation Recognition
Situation Recognition is the task of generating a structured summary of what is happening in an image using an activity verb and the semantic roles played by actors and objects.
Ranked #1 on
Situation Recognition
on imSitu
Revealing the Illusion of Joint Multimodal Understanding in VideoQA Models
We evaluate models on CLAVI and find that all models achieve high performance on multimodal shortcut instances, but most of them have poor performance on the counterfactual instances that necessitate joint multimodal understanding.
Modelling Spatio-Temporal Interactions for Compositional Action Recognition
The final context-infused spatio-temporal interaction tokens are used for compositional action recognition.
A Region-Prompted Adapter Tuning for Visual Abductive Reasoning
Existing works highlight cues utilizing a specific prompt (e. g., colorful prompt).
Ranked #1 on
Visual Abductive Reasoning
on SHERLOCK
Energy-based Self-Training and Normalization for Unsupervised Domain Adaptation
EBL can be used to improve the instance selection for a self-training task on the unlabelled target domain, and 2. alignment and normalizing energy scores can learn domain-invariant representations.
Who are you referring to? Coreference resolution in image narrations
Coreference resolution aims to identify words and phrases which refer to same entity in a text, a core task in natural language processing.
Interaction Region Visual Transformer for Egocentric Action Anticipation
On the EK100 evaluation server, InAViT is the top-performing method on the public leaderboard (at the time of submission) where it outperforms the second-best model by 3. 3% on mean-top5 recall.
Ranked #1 on
Action Anticipation
on EGTEA
Abductive Action Inference
In this paper, we introduce a novel research task known as "abductive action inference" which addresses the question of which actions were executed by a human to reach a specific state shown in a single snapshot.
Predicting the Next Action by Modeling the Abstract Goal
It is through the submission of this paper that our method is currently the new state-of-the-art for action anticipation in EK55 and EGTEA Gaze+ https://competitions. codalab. org/competitions/20071#results Code available at https://github. com/debadityaroy/Abstract_Goal
Consistency Regularization for Domain Adaptation
Collection of real world annotations for training semantic segmentation models is an expensive process.
3D Equivariant Graph Implicit Functions
In this work, we address two key limitations of such representations, in failing to capture local 3D geometric fine details, and to learn from and generalize to shapes with unseen 3D transformations.
LocFormer: Enabling Transformers to Perform Temporal Moment Localization on Long Untrimmed Videos With a Feature Sampling Approach
We propose LocFormer, a Transformer-based model for video grounding which operates at a constant memory footprint regardless of the video length, i. e. number of frames.
TDAM: Top-Down Attention Module for Contextually Guided Feature Selection in CNNs
Attention modules for Convolutional Neural Networks (CNNs) are an effective method to enhance performance on multiple computer-vision tasks.
Not All Relations are Equal: Mining Informative Labels for Scene Graph Generation
Scene graph generation (SGG) aims to capture a wide variety of interactions between pairs of objects, which is essential for full scene understanding.
Action Forecasting with Feature-wise Self-Attention
A temporal recurrent encoder captures temporal information of input videos while a self-attention model is used to attend on relevant feature dimensions of the input space.
Anticipating human actions by correlating past with the future with Jaccard similarity measures
We propose a framework for early action recognition and anticipation by correlating past features with the future using three novel similarity measures called Jaccard vector similarity, Jaccard cross-correlation and Jaccard Frobenius inner product over covariances.
A Log-likelihood Regularized KL Divergence for Video Prediction with A 3D Convolutional Variational Recurrent Network
In this paper, we introduce a new variational model that extends the recurrent network in two ways for the task of video frame prediction.
FlowCaps: Optical Flow Estimation with Capsule Networks For Action Recognition
Capsule networks (CapsNets) have recently shown promise to excel in most computer vision tasks, especially pertaining to scene understanding.
DORi: Discovering Object Relationship for Moment Localization of a Natural-Language Query in Video
This paper studies the task of temporal moment localization in a long untrimmed video using natural language query.
Inferring Temporal Compositions of Actions Using Probabilistic Automata
This paper presents a framework to recognize temporal compositions of atomic actions in videos.
Forecasting future action sequences with attention: a new approach to weakly supervised action forecasting
We extend our action sequence forecasting model to perform weakly supervised action forecasting on two challenging datasets, the Breakfast and the 50Salads.
Injecting Prior Knowledge into Image Caption Generation
Automatically generating natural language descriptions from an image is a challenging problem in artificial intelligence that requires a good understanding of the visual and textual signals and the correlations between them.
Action Anticipation with RBF Kernelized Feature Mapping RNN
We introduce a novel Recurrent Neural Network-based algorithm for future video feature generation and action anticipation called feature mapping RNN.
Human Action Sequence Classification
Furthermore, we use our model that is trained to output action sequences to solve downstream tasks; such as video captioning and action localization.
Deep Multiple Instance Learning with Gaussian Weighting
The instance representation is shared by both instance classification and weighting streams.
Weakly Supervised Gaussian Networks for Action Detection
Detecting temporal extents of human actions in videos is a challenging computer vision problem that requires detailed manual supervision including frame-level labels.
VIENA2: A Driving Anticipation Dataset
Action anticipation is critical in scenarios where one needs to react before the action is finalized.
Face Super-resolution Guided by Facial Component Heatmaps
State-of-the-art face super-resolution methods use deep convolutional neural networks to learn a mapping between low-resolution (LR) facial patterns and their corresponding high-resolution (HR) counterparts by exploring local information.
Action Anticipation By Predicting Future Dynamic Images
Human action-anticipation methods predict what is the future action by observing only a few portion of an action in progress.
Super-Resolving Very Low-Resolution Face Images With Supplementary Attributes
An LR input contains low-frequency facial components of its HR version while its residual face image defined as the difference between the HR ground-truth and interpolated LR images contains the missing high-frequency facial details.
Neural Algebra of Classifiers
In this paper, we build on the compositionality principle and develop an "algebra" to compose classifiers for complex visual concepts.
Discriminatively Learned Hierarchical Rank Pooling Networks
First, we present "discriminative rank pooling" in which the shared weights of our video representation and the parameters of the action classifiers are estimated jointly for a given training dataset of labelled vector sequences using a bilevel optimization formulation of the learning problem.
DeepPermNet: Visual Permutation Learning
Unrolling these iterations in a Sinkhorn network layer, we propose DeepPermNet, an end-to-end CNN model for this task.
Generalized Rank Pooling for Activity Recognition
Most popular deep models for action recognition split video sequences into short sub-sequences consisting of a few frames; frame-based features are then pooled for recognizing the activity.
Encouraging LSTMs to Anticipate Actions Very Early
In contrast to the widely studied problem of recognizing an action given a complete sequence, action anticipation aims to identify the action from only partially available videos.
Deep Learning for Automated Quality Assessment of Color Fundus Images in Diabetic Retinopathy Screening
Three retinal image analysis experts were employed to categorize these images into Accept and Reject classes based on the precise definition of image quality in the context of DR. A deep learning framework was trained using 3428 images.
Unsupervised Human Action Detection by Action Matching
On the MPII Cooking dataset we detect action segments with a precision of 21. 6% and recall of 11. 7% over 946 long video pairs and over 5000 ground truth action segments.
Guided Open Vocabulary Image Captioning with Constrained Beam Search
Existing image captioning models do not generalize well to out-of-domain images containing novel scenes or objects.
Action Recognition with Dynamic Image Networks
This is a powerful idea because it allows to convert any video to an image so that existing CNN models pre-trained for the analysis of still images can be immediately extended to videos.
Self-Supervised Video Representation Learning With Odd-One-Out Networks
On action classification, our method obtains 60. 3\% on the UCF101 dataset using only UCF101 data for training which is approximately 10% better than current state-of-the-art self-supervised learning methods.
Ranked #47 on
Self-Supervised Action Recognition
on UCF101
Deep Action- and Context-Aware Sequence Learning for Activity Recognition and Anticipation
We outperform the state-of-the-art methods that, as us, rely only on RGB frames as input for both action recognition and anticipation.
Generalized BackPropagation, Étude De Cas: Orthogonality
This paper introduces an extension of the backpropagation algorithm that enables us to have layers with constrained weights in a deep network.
Dimensionality Reduction
Fine-Grained Image Classification
+1
SPICE: Semantic Propositional Image Caption Evaluation
There is considerable interest in the task of automatically generating image captions.
On Differentiating Parameterized Argmin and Argmax Problems with Application to Bi-level Optimization
Some recent works in machine learning and computer vision involve the solution of a bi-level optimization problem.
Discriminative Hierarchical Rank Pooling for Activity Recognition
We present hierarchical rank pooling, a video sequence encoding method for activity recognition.
Dynamic Image Networks for Action Recognition
We introduce the concept of dynamic image, a novel compact representation of videos useful for video analysis especially when convolutional neural networks (CNNs) are used.
Ranked #62 on
Action Recognition
on HMDB-51
Rank Pooling for Action Recognition
We show how the parameters of a function that has been fit to the video data can serve as a robust new video representation.
Guiding the Long-Short Term Memory Model for Image Caption Generation
In this work we focus on the problem of image caption generation.
Learning to Rank Based on Subsequences
We present a supervised learning to rank algorithm that effectively orders images by exploiting the structure in image sequences.
MidRank: Learning to rank based on subsequences
We present a supervised learning to rank algorithm that effectively orders images by exploiting the structure in image sequences.
Guiding Long-Short Term Memory for Image Caption Generation
In this work we focus on the problem of image caption generation.
Dataset Fingerprints: Exploring Image Collections Through Data Mining
As the amount of visual data increases, so does the need for summarization tools that can be used to explore large image collections and to quickly get familiar with their content.
Modeling Video Evolution for Action Recognition
We postulate that a function capable of ordering the frames of a video temporally (based on the appearance) captures well the evolution of the appearance within the video.
Object Class Detection and Classification using Multi Scale Gradient and Corner Point based Shape Descriptors
This paper presents a novel multi scale gradient and a corner point based shape descriptors.
Joint cross-domain classification and subspace learning for unsupervised adaptation
Domain adaptation aims at adapting the knowledge acquired on a source domain to a new different but related target domain.
Location Recognition Over Large Time Lags
Would it be possible to automatically associate ancient pictures to modern ones and create fancy cultural heritage city maps?
Subspace Alignment For Domain Adaptation
We present two approaches to determine the only hyper-parameter in our method corresponding to the size of the subspaces.
