Search Results for author:
Found 36 papers, 15 papers with code
OStr-DARTS: Differentiable Neural Architecture Search based on Operation Strength
Differentiable architecture search (DARTS) has emerged as a promising technique for effective neural architecture search, and it mainly contains two steps to find the high-performance architecture: First, the DARTS supernet that consists of mixed operations will be optimized via gradient descent.
Rethinking the Architecture Design for Efficient Generic Event Boundary Detection
Generic event boundary detection (GEBD), inspired by human visual cognitive behaviors of consistently segmenting videos into meaningful temporal chunks, finds utility in various applications such as video editing and.
Fine-grained Dynamic Network for Generic Event Boundary Detection
Generic event boundary detection (GEBD) aims at pinpointing event boundaries naturally perceived by humans, playing a crucial role in understanding long-form videos.
DyFADet: Dynamic Feature Aggregation for Temporal Action Detection
Based on DFA, the proposed dynamic encoder layer aggregates the temporal features within the action time ranges and guarantees the discriminability of the extracted representations.
Ranked #3 on
Temporal Action Localization
on HACS
Typography Leads Semantic Diversifying: Amplifying Adversarial Transferability across Multimodal Large Language Models
Following the advent of the Artificial Intelligence (AI) era of large models, Multimodal Large Language Models (MLLMs) with the ability to understand cross-modal interactions between vision and text have attracted wide attention.
EVAN: Evolutional Video Streaming Adaptation via Neural Representation
Neural representation for video (NeRV), which embeds the video content into neural network weights, allows video reconstruction with incomplete models.
Privacy-Preserving End-to-End Spoken Language Understanding
Thus, the SLU system needs to ensure that a potential malicious attacker cannot deduce the sensitive attributes of the users, while it should avoid greatly compromising the SLU accuracy.
Adaptive Hybrid Masking Strategy for Privacy-Preserving Face Recognition Against Model Inversion Attack
Specifically, face images are masked in the frequency domain using an adaptive MixUp strategy.
Unveiling Typographic Deceptions: Insights of the Typographic Vulnerability in Large Vision-Language Model
Large Vision-Language Models (LVLMs) rely on vision encoders and Large Language Models (LLMs) to exhibit remarkable capabilities on various multi-modal tasks in the joint space of vision and language.
The Random Forest Model for Analyzing and Forecasting the US Stock Market in the Context of Smart Finance
The stock market is a crucial component of the financial market, playing a vital role in wealth accumulation for investors, financing costs for listed companies, and the stable development of the national macroeconomy.
AI-Driven Anonymization: Protecting Personal Data Privacy While Leveraging Machine Learning
It achieves personal data privacy protection and detection through the use of machine learning's differential privacy protection algorithm.
Optimizing Portfolio Management and Risk Assessment in Digital Assets Using Deep Learning for Predictive Analysis
Finally, in this paper, the strategy is implemented by selecting the assets and actions with the largest Q value.
Pursing the Sparse Limitation of Spiking Deep Learning Structures
It posits that within dense neural networks, there exist winning tickets or subnetworks that are sparser but do not compromise performance.
Once-Training-All-Fine: No-Reference Point Cloud Quality Assessment via Domain-relevance Degradation Description
Second, to reduce the significant domain discrepancy, we establish an intermediate domain, the description domain, based on insights from subjective experiments, by considering the domain relevance among samples located in the perception domain and learning a structured latent space.
Fixing Overconfidence in Dynamic Neural Networks
Dynamic neural networks are a recent technique that promises a remedy for the increasing size of modern deep learning models by dynamically adapting their computational cost to the difficulty of the inputs.
Revisiting Long-tailed Image Classification: Survey and Benchmarks with New Evaluation Metrics
We set up novel evaluation benchmarks based on a series of testing sets with evolving distributions.
Ranked #65 on
Long-tail Learning
on CIFAR-100-LT (ρ=100)
Proportionate Recursive Maximum Correntropy Criterion Adaptive Filtering Algorithms and their Performance Analysis
Motivated by the success of our recently proposed proportionate recursive least squares (PRLS) algorithm for sparse system identification, we propose to introduce the proportionate updating (PU) mechanism into the RMCC, leading to two sparsity-aware RMCC algorithms: the proportionate recursive MCC (PRMCC) algorithm and the combinational PRMCC (CPRMCC) algorithm.
TCDM: Transformational Complexity Based Distortion Metric for Perceptual Point Cloud Quality Assessment
The goal of objective point cloud quality assessment (PCQA) research is to develop quantitative metrics that measure point cloud quality in a perceptually consistent manner.
Structured Attention Composition for Temporal Action Localization
To tackle this issue, we make an early effort to study temporal action localization from the perspective of multi-modality feature learning, based on the observation that different actions exhibit specific preferences to appearance or motion modality.
Colar: Effective and Efficient Online Action Detection by Consulting Exemplars
Based on the exemplar-consultation mechanism, the long-term dependencies can be captured by regarding historical frames as exemplars, while the category-level modeling can be achieved by regarding representative frames from a category as exemplars.
Ranked #6 on
Online Action Detection
on TVSeries
Background-Click Supervision for Temporal Action Localization
Weakly supervised temporal action localization aims at learning the instance-level action pattern from the video-level labels, where a significant challenge is action-context confusion.
CondenseNet V2: Sparse Feature Reactivation for Deep Networks
Reusing features in deep networks through dense connectivity is an effective way to achieve high computational efficiency.
Enhanced Medium Range Order in Vapor Deposited Germania Glasses at Elevated Temperatures
Herein, we show the atomic arrangement of strong network forming GeO2 glass is modified at medium range (< 2 nm) through vapor deposition at elevated temperatures.
Materials Science
Dynamic Neural Networks: A Survey
Dynamic neural network is an emerging research topic in deep learning.
Revisiting Locally Supervised Learning: an Alternative to End-to-end Training
Due to the need to store the intermediate activations for back-propagation, end-to-end (E2E) training of deep networks usually suffers from high GPUs memory footprint.
Revisiting Locally Supervised Training of Deep Neural Networks
As InfoPro loss is difficult to compute in its original form, we derive a feasible upper bound as a surrogate optimization objective, yielding a simple but effective algorithm.
Point Cloud Quality Assessment: Dataset Construction and Learning-based No-Reference Metric
Full-reference (FR) point cloud quality assessment (PCQA) has achieved impressive progress in recent years.
Ranked #5 on
Point Cloud Quality Assessment
on WPC
Glance and Focus: a Dynamic Approach to Reducing Spatial Redundancy in Image Classification
The accuracy of deep convolutional neural networks (CNNs) generally improves when fueled with high resolution images.
Structural evolution of binary oxide nanolaminates with annealing and its impact on room-temperature internal friction
Internal friction in oxide thin films imposes a critical limitation to the sensitivity and stability of ultra-high finesse optical cavities for gravitational wave detectors.
Materials Science
Revisiting Anchor Mechanisms for Temporal Action Localization
To address this problem, this paper proposes a novel anchor-free action localization module that assists action localization by temporal points.
Equivalent Classification Mapping for Weakly Supervised Temporal Action Localization
The existing methods can be categorized into two localization-by-classification pipelines, i. e., the pre-classification pipeline and the post-classification pipeline.
Resolution Adaptive Networks for Efficient Inference
Adaptive inference is an effective mechanism to achieve a dynamic tradeoff between accuracy and computational cost in deep networks.
Learning Sparse 2D Temporal Adjacent Networks for Temporal Action Localization
In this report, we introduce the Winner method for HACS Temporal Action Localization Challenge 2019.
Ensemble Kalman Filtering for Online Gaussian Process Regression and Learning
The ensemble Kalman filter reduces the computational complexity required to obtain predictions with Gaussian processes preserving the accuracy level of these predictions.
Reinforcement Cutting-Agent Learning for Video Object Segmentation
In this paper, we formulate this problem as a Markov Decision Process, where agents are learned to segment object regions under a deep reinforcement learning framework.
SPFTN: A Self-Paced Fine-Tuning Network for Segmenting Objects in Weakly Labelled Videos
Object segmentation in weakly labelled videos is an interesting yet challenging task, which aims at learning to perform category-specific video object segmentation by only using video-level tags.
