Search Results for author:
Found 26 papers, 14 papers with code
BAMM: Bidirectional Autoregressive Motion Model
To address these challenges, we propose Bidirectional Autoregressive Motion Model (BAMM), a novel text-to-motion generation framework.
Analysis and Detection of Multilingual Hate Speech Using Transformer Based Deep Learning
In this work, the proposed method is using transformer-based model to detect hate speech in social media, like twitter, Facebook, WhatsApp, Instagram, etc.
SI-MIL: Taming Deep MIL for Self-Interpretability in Gigapixel Histopathology
Introducing interpretability and reasoning into Multiple Instance Learning (MIL) methods for Whole Slide Image (WSI) analysis is challenging, given the complexity of gigapixel slides.
Multiview Aerial Visual Recognition (MAVREC): Can Multi-view Improve Aerial Visual Perception?
Despite the commercial abundance of UAVs, aerial data acquisition remains challenging, and the existing Asia and North America-centric open-source UAV datasets are small-scale or low-resolution and lack diversity in scene contextuality.
Just Add $π$! Pose Induced Video Transformers for Understanding Activities of Daily Living
To facilitate the adoption of video transformers for ADL, we hypothesize that the augmentation of RGB with human pose information, known for its sensitivity to fine-grained motion and multiple viewpoints, is essential.
Ranked #1 on
Action Classification
on Toyota Smarthome dataset
(using extra training data)
Limited Data, Unlimited Potential: A Study on ViTs Augmented by Masked Autoencoders
We explore the appropriate SSL tasks that can be optimized alongside the primary task, the training schemes for these tasks, and the data scale at which they can be most effective.
Attention De-sparsification Matters: Inducing Diversity in Digital Pathology Representation Learning
We propose DiRL, a Diversity-inducing Representation Learning technique for histopathology imaging.
Attending Generalizability in Course of Deep Fake Detection by Exploring Multi-task Learning
This work explores various ways of exploring multi-task learning (MTL) techniques aimed at classifying videos as original or manipulated in cross-manipulation scenario to attend generalizability in deep fake scenario.
Seeing the Pose in the Pixels: Learning Pose-Aware Representations in Vision Transformers
Both PAAT and PAAB surpass their respective backbone Transformers by up to 9. 8% in real-world action recognition and 21. 8% in multi-view robotic video alignment.
Video + CLIP Baseline for Ego4D Long-term Action Anticipation
The CLIP embedding provides fine-grained understanding of objects relevant for an action whereas the slowfast network is responsible for modeling temporal information within a video clip of few frames.
Learning Viewpoint-Agnostic Visual Representations by Recovering Tokens in 3D Space
To this end, we propose a 3D Token Representation Layer (3DTRL) that estimates the 3D positional information of the visual tokens and leverages it for learning viewpoint-agnostic representations.
Does Self-supervised Learning Really Improve Reinforcement Learning from Pixels?
We investigate whether self-supervised learning (SSL) can improve online reinforcement learning (RL) from pixels.
CD-Net: Histopathology Representation Learning using Pyramidal Context-Detail Network
To jointly leverage complementary information from multiple resolutions, we present a novel transformer based Pyramidal Context-Detail Network (CD-Net).
MS-TCT: Multi-Scale Temporal ConvTransformer for Action Detection
Action detection is an essential and challenging task, especially for densely labelled datasets of untrimmed videos.
Ranked #2 on
Action Detection
on TSU
ViewCLR: Learning Self-supervised Video Representation for Unseen Viewpoints
Learning self-supervised video representation predominantly focuses on discriminating instances generated from simple data augmentation schemes.
Cross-modal Manifold Cutmix for Self-supervised Video Representation Learning
To this end, we propose Cross-Modal Manifold Cutmix (CMMC) that inserts a video tesseract into another video tesseract in the feature space across two different modalities.
CTRN: Class-Temporal Relational Network for Action Detection
Action detection is an essential and challenging task, especially for densely labelled datasets of untrimmed videos.
Ranked #2 on
Action Detection
on Multi-THUMOS
Vi-MIX FOR SELF-SUPERVISED VIDEO REPRESENTATION
We find that our video mixing strategy: Vi-Mix, i. e. preliminary mixing of videos followed by CMMC across different modalities in a video, improves the qual- ity of learned video representations.
Weakly-supervised Joint Anomaly Detection and Classification
Thinking of a fully automatized surveillance system, which is capable of both detecting and classifying the anomalies that need immediate actions, a joint anomaly detection and classification method is a pressing need.
Learning an Augmented RGB Representation with Cross-Modal Knowledge Distillation for Action Detection
On the other hand, sequence-level distillation encourages the student to learn the temporal knowledge from the teacher, which consists of transferring the Global Contextual Relations and the Action Boundary Saliency.
VPN++: Rethinking Video-Pose embeddings for understanding Activities of Daily Living
But the cost of computing 3D poses from RGB stream is high in the absence of appropriate sensors.
Ranked #9 on
Action Recognition
on NTU RGB+D 120
(using extra training data)
PDAN: Pyramid Dilated Attention Network for Action Detection
Previous action detection methods fail in selecting the key temporal information in long videos.
Ranked #1 on
Action Detection
on TSU
Toyota Smarthome Untrimmed: Real-World Untrimmed Videos for Activity Detection
Therefore, we propose a new baseline method for activity detection to tackle the novel challenges provided by our dataset.
VPN: Learning Video-Pose Embedding for Activities of Daily Living
The 2 key components of this VPN are a spatial embedding and an attention network.
Ranked #6 on
Action Classification
on Toyota Smarthome dataset
(using extra training data)
Toyota Smarthome: Real-World Activities of Daily Living
As recent activity recognition approaches fail to address the challenges posed by Toyota Smarthome, we present a novel activity recognition method with attention mechanism.
Ranked #7 on
Action Classification
on Toyota Smarthome dataset
(using extra training data)
Deep-Temporal LSTM for Daily Living Action Recognition
In this paper, we propose to improve the traditional use of RNNs by employing a many to many model for video classification.
