Related papers: After All, Only The Last Neuron Matters: Comparing…

Prior to the introduction of Graph Neural Networks (GNNs), modeling and analyzing irregular data, particularly graphs, was thought to be the Achilles' heel of deep learning. The core concept of GNNs is to find a representation by…

Top-leading solutions for Video Scene Graph Generation (VSGG) typically adopt an offline pipeline. Though demonstrating promising performance, they remain unable to handle real-time video streams and consume large GPU memory. Moreover,…

With the rapid advancement of diffusion-based generative models, Stable Diffusion (SD) has emerged as a state-of-the-art framework for high-fidelity im-age synthesis. However, existing SD models suffer from suboptimal feature aggregation,…

Scene graph generation (SGG) is built on top of detected objects to predict object pairwise visual relations for describing the image content abstraction. Existing works have revealed that if the links between objects are given as prior…

Scene graph generation refers to the task of automatically mapping an image into a semantic structural graph, which requires correctly labeling each extracted object and their interaction relationships. Despite the recent success in object…

Research in scene graph generation has quickly gained traction in the past few years because of its potential to help in downstream tasks like visual question answering, image captioning, etc. Many interesting approaches have been proposed…

Camera and lidar are important sensor modalities for robotics in general and self-driving cars in particular. The sensors provide complementary information offering an opportunity for tight sensor-fusion. Surprisingly, lidar-only methods…

This paper considers a video caption generating network referred to as Semantic Grouping Network (SGN) that attempts (1) to group video frames with discriminating word phrases of partially decoded caption and then (2) to decode those…

Few-shot semantic segmentation (FSS) aims to achieve novel objects segmentation with only a few annotated samples and has made great progress recently. Most of the existing FSS models focus on the feature matching between support and query…

Vision Foundation Models (VFMs) have demonstrated impressive representational capabilities. However, adapting them to downstream tasks via full fine-tuning incurs prohibitive computational and storage overhead. Parameter-Efficient…

We propose a novel semi-supervised, Multi-Level Sequential Generative Adversarial Network (MLS-GAN) architecture for group activity recognition. In contrast to previous works which utilise manually annotated individual human action…

We propose a novel Graph Neural Network (GNN) model, named DeepStateGNN, for analyzing traffic data, demonstrating its efficacy in two critical tasks: forecasting and reconstruction. Unlike typical GNN methods that treat each traffic sensor…

Accurate multivariate time series forecasting hinges on inter-series correlations, which often evolve in complex ways across different temporal scales. Existing methods are limited in modeling these multi-scale dependencies and struggle to…

Action recognition is an exciting research avenue for artificial intelligence since it may be a game changer in the emerging industrial fields such as robotic visions and automobiles. However, current deep learning faces major challenges…

Robot vision is a fundamental device for human-robot interaction and robot complex tasks. In this paper, we use Kinect and propose a feature graph fusion (FGF) for robot recognition. Our feature fusion utilizes RGB and depth information to…

Scene Graph Generation (SGG) serves a comprehensive representation of the images for human understanding as well as visual understanding tasks. Due to the long tail bias problem of the object and predicate labels in the available annotated…

Residual Neural Networks [1] won first place in all five main tracks of the ImageNet and COCO 2015 competitions. This kind of network involves the creation of pluggable modules such that the output contains a residual from the input. The…

Lidars and cameras are critical sensors that provide complementary information for 3D detection in autonomous driving. While most prevalent methods progressively downscale the 3D point clouds and camera images and then fuse the high-level…

SCGAN adds a similarity constraint between generated images and conditions as a regularization term on generative adversarial networks. Similarity constraint works as a tutor to instruct the generator network to comprehend the difference of…

Action recognition has been a heated topic in computer vision for its wide application in vision systems. Previous approaches achieve improvement by fusing the modalities of the skeleton sequence and RGB video. However, such methods have a…