Search Results for author:
Found 19 papers, 5 papers with code
Convolutional Prompting meets Language Models for Continual Learning
Continual Learning (CL) enables machine learning models to learn from continuously shifting new training data in absence of data from old tasks.
Goals are Enough: Inducing AdHoc cooperation among unseen Multi-Agent systems in IMFs
Often there exists a hierarchical structure of intent fulfilment where multiple pre-trained, self-interested agents may need to be further orchestrated by a supervisor or controller agent.
Exemplar-Free Continual Transformer with Convolutions
Although there have been some recent CL approaches for vision transformers, they either store training instances of previous tasks or require a task identifier during test time, which can be limiting.
Domain Adaptation of Reinforcement Learning Agents based on Network Service Proximity
The dynamic and evolutionary nature of service requirements in wireless networks has motivated the telecom industry to consider intelligent self-adapting Reinforcement Learning (RL) agents for controlling the growing portfolio of network services.
Few-Shot Visual Question Generation: A Novel Task and Benchmark Datasets
In this paper, we propose a new and challenging Few-Shot Visual Question Generation (FS-VQG) task and provide a comprehensive benchmark to it.
Reinforcement Explanation Learning
Black-box methods to generate saliency maps are particularly interesting due to the fact that they do not utilize the internals of the model to explain the decision.
Contrast and Mix: Temporal Contrastive Video Domain Adaptation with Background Mixing
Unsupervised domain adaptation which aims to adapt models trained on a labeled source domain to a completely unlabeled target domain has attracted much attention in recent years.
Ranked #2 on
Unsupervised Domain Adaptation
on UCF-HMDB
Semi-Supervised Action Recognition with Temporal Contrastive Learning
We approach this problem by learning a two-pathway temporal contrastive model using unlabeled videos at two different speeds leveraging the fact that changing video speed does not change an action.
Select, Label, and Mix: Learning Discriminative Invariant Feature Representations for Partial Domain Adaptation
Partial domain adaptation which assumes that the unknown target label space is a subset of the source label space has attracted much attention in computer vision.
Ranked #1 on
Partial Domain Adaptation
on Office-31
Mitigating Dataset Imbalance via Joint Generation and Classification
In this work we address these questions from the perspective of dataset imbalance resulting out of severe under-representation of annotated training data for certain classes and its effect on both deep classification and generation methods.
Revisiting Few-shot Activity Detection with Class Similarity Control
In this paper, we present a conceptually simple and general yet novel framework for few-shot temporal activity detection based on proposal regression which detects the start and end time of the activities in untrimmed videos.
Two-Stream Region Convolutional 3D Network for Temporal Activity Detection
We address the problem of temporal activity detection in continuous, untrimmed video streams.
Ranked #4 on
Action Recognition
on THUMOS’14
RISE: Randomized Input Sampling for Explanation of Black-box Models
We compare our approach to state-of-the-art importance extraction methods using both an automatic deletion/insertion metric and a pointing metric based on human-annotated object segments.
Weakly Supervised Summarization of Web Videos
Casting the problem as a weakly supervised learning problem, we propose a flexible deep 3D CNN architecture to learn the notion of importance using only video-level annotation, and without any human-crafted training data.
R-C3D: Region Convolutional 3D Network for Temporal Activity Detection
We address the problem of activity detection in continuous, untrimmed video streams.
Ranked #1 on
Action Recognition In Videos
on THUMOS’14
Top-down Visual Saliency Guided by Captions
Neural image/video captioning models can generate accurate descriptions, but their internal process of mapping regions to words is a black box and therefore difficult to explain.
Video Summarization in a Multi-View Camera Network
While most existing video summarization approaches aim to extract an informative summary of a single video, we propose a novel framework for summarizing multi-view videos by exploiting both intra- and inter-view content correlations in a joint embedding space.
Temporal Model Adaptation for Person Re-Identification
Person re-identification is an open and challenging problem in computer vision.
Continuous Adaptation of Multi-Camera Person Identification Models through Sparse Non-redundant Representative Selection
We demonstrate the effectiveness of our approach on multi-camera person re-identification datasets, to demonstrate the feasibility of learning online classification models in multi-camera big data applications.
