Search Results for author:
Found 29 papers, 15 papers with code
Not All Models Localize Linguistic Knowledge in the Same Place: A Layer-wise Probing on BERToids’ Representations
Most of the recent works on probing representations have focused on BERT, with the presumption that the findings might be similar to the other models.
Evaluating Human Alignment and Model Faithfulness of LLM Rationale
We study how well large language models (LLMs) explain their generations with rationales -- a set of tokens extracted from the input texts that reflect the decision process of LLMs.
Occlusion Handling in 3D Human Pose Estimation with Perturbed Positional Encoding
To this end, we propose a novel positional encoding technique, PerturbPE, that extracts consistent and regular components from the eigenbasis.
MemLLM: Finetuning LLMs to Use An Explicit Read-Write Memory
While current large language models (LLMs) demonstrate some capabilities in knowledge-intensive tasks, they are limited by relying on their parameters as an implicit storage mechanism.
DecompX: Explaining Transformers Decisions by Propagating Token Decomposition
An emerging solution for explaining Transformer-based models is to use vector-based analysis on how the representations are formed.
RET-LLM: Towards a General Read-Write Memory for Large Language Models
Large language models (LLMs) have significantly advanced the field of natural language processing (NLP) through their extensive parameters and comprehensive data utilization.
Diffusion Models for Medical Image Analysis: A Comprehensive Survey
Then, we provide a systematic taxonomy of diffusion models in the medical domain and propose a multi-perspective categorization based on their application, imaging modality, organ of interest, and algorithms.
BERT on a Data Diet: Finding Important Examples by Gradient-Based Pruning
In this work, we employ these two metrics for the first time in NLP.
GlobEnc: Quantifying Global Token Attribution by Incorporating the Whole Encoder Layer in Transformers
There has been a growing interest in interpreting the underlying dynamics of Transformers.
Metaphors in Pre-Trained Language Models: Probing and Generalization Across Datasets and Languages
Large pre-trained language models (PLMs) are therefore assumed to encode metaphorical knowledge useful for NLP systems.
Adaptive Token Sampling For Efficient Vision Transformers
Since ATS is a parameter-free module, it can be added to the off-the-shelf pre-trained vision transformers as a plug and play module, thus reducing their GFLOPs without any additional training.
Ranked #13 on
Efficient ViTs
on ImageNet-1K (with DeiT-S)
TaylorSwiftNet: Taylor Driven Temporal Modeling for Swift Future Frame Prediction
While recurrent neural networks (RNNs) demonstrate outstanding capabilities for future video frame prediction, they model dynamics in a discrete time space, i. e., they predict the frames sequentially with a fixed temporal step.
Long Short View Feature Decomposition via Contrastive Video Representation Learning
We argue that a single representation to capture both types of features is sub-optimal, and propose to decompose the representation space into stationary and non-stationary features via contrastive learning from long and short views, i. e. long video sequences and their shorter sub-sequences.
Not All Models Localize Linguistic Knowledge in the Same Place: A Layer-wise Probing on BERToids' Representations
Most of the recent works on probing representations have focused on BERT, with the presumption that the findings might be similar to the other models.
3D CNNs with Adaptive Temporal Feature Resolutions
While the GFLOPs of a 3D CNN can be decreased by reducing the temporal feature resolution within the network, there is no setting that is optimal for all input clips.
SCT: Set Constrained Temporal Transformer for Set Supervised Action Segmentation
In addition, the network estimates the action labels for each frame.
Large Scale Holistic Video Understanding
HVU is organized hierarchically in a semantic taxonomy that focuses on multi-label and multi-task video understanding as a comprehensive problem that encompasses the recognition of multiple semantic aspects in the dynamic scene.
Ranked #11 on
Action Recognition
on UCF101
Fast Weakly Supervised Action Segmentation Using Mutual Consistency
Action segmentation is the task of predicting the actions for each frame of a video.
Segmentation
Weakly Supervised Action Segmentation (Transcript)
Online Signature Verification using Deep Representation: A new Descriptor
To deal with these difficulties and modeling the signatures efficiently, we propose a method that a one-class classifier per each user is built on discriminative features.
Spatio-Temporal Channel Correlation Networks for Action Classification
Our experiments show that adding STC blocks to current state-of-the-art architectures outperforms the state-of-the-art methods on the HMDB51, UCF101 and Kinetics datasets.
Semantic Video Segmentation: A Review on Recent Approaches
This paper gives an overview on semantic segmentation consists of an explanation of this field, it's status and relation with other vision fundamental tasks, different datasets and common evaluation parameters that have been used by researchers.
AVID: Adversarial Visual Irregularity Detection
Real-time detection of irregularities in visual data is very invaluable and useful in many prospective applications including surveillance, patient monitoring systems, etc.
Towards Principled Design of Deep Convolutional Networks: Introducing SimpNet
SimpNet outperforms the deeper and more complex architectures such as VGGNet, ResNet, WideResidualNet \etc, on several well-known benchmarks, while having 2 to 25 times fewer number of parameters and operations.
Ranked #118 on
Image Classification
on CIFAR-10
Temporal 3D ConvNets: New Architecture and Transfer Learning for Video Classification
Thus, by finetuning this network, we beat the performance of generic and recent methods in 3D CNNs, which were trained on large video datasets, e. g. Sports-1M, and finetuned on the target datasets, e. g. HMDB51/UCF101.
Deep-Anomaly: Fully Convolutional Neural Network for Fast Anomaly Detection in Crowded Scenes
The detection of abnormal behaviours in crowded scenes has to deal with many challenges.
Lets keep it simple, Using simple architectures to outperform deeper and more complex architectures
Our simple 13-layer architecture outperforms most of the deeper and complex architectures to date such as VGGNet, ResNet, and GoogleNet on several well-known benchmarks while having 2 to 25 times fewer number of parameters and operations.
Ranked #10 on
Image Classification
on MNIST
STFCN: Spatio-Temporal FCN for Semantic Video Segmentation
Current work on convolutional neural networks(CNNs) has shown that CNNs provide advanced spatial features supporting a very good performance of solutions for both image and video analysis, especially for the semantic segmentation task.
A Novel Approach For Finger Vein Verification Based on Self-Taught Learning
In this paper, we propose a method for user Finger Vein Authentication (FVA) as a biometric system.
Feature Representation for Online Signature Verification
Biometrics systems have been used in a wide range of applications and have improved people authentication.
