Search Results for author:
Found 25 papers, 14 papers with code
EgoObjects: A Large-Scale Egocentric Dataset for Fine-Grained Object Understanding
To bootstrap the research on EgoObjects, we present a suite of 4 benchmark tasks around the egocentric object understanding, including a novel instance level- and the classical category level object detection.
Exploring Open-Vocabulary Semantic Segmentation without Human Labels
Although acquired extensive knowledge of visual concepts, it is non-trivial to exploit knowledge from these VL models to the task of semantic segmentation, as they are usually trained at an image level.
Going Denser with Open-Vocabulary Part Segmentation
In this paper, we propose a detector with the ability to predict both open-vocabulary objects and their part segmentation.
Exploring Open-Vocabulary Semantic Segmentation from CLIP Vision Encoder Distillation Only
Semantic segmentation is a crucial task in computer vision that involves segmenting images into semantically meaningful regions at the pixel level.
3rd Continual Learning Workshop Challenge on Egocentric Category and Instance Level Object Understanding
Continual Learning, also known as Lifelong or Incremental Learning, has recently gained renewed interest among the Artificial Intelligence research community.
Unified Transformer Tracker for Object Tracking
Although UniTrack \cite{wang2021different} demonstrates that a shared appearance model with multiple heads can be used to tackle individual tracking tasks, it fails to exploit the large-scale tracking datasets for training and performs poorly on single object tracking.
Auto-X3D: Ultra-Efficient Video Understanding via Finer-Grained Neural Architecture Search
Efficient video architecture is the key to deploying video recognition systems on devices with limited computing resources.
NASViT: Neural Architecture Search for Efficient Vision Transformers with Gradient Conflict aware Supernet Training
In this work, we observe that the poor performance is due to a gradient conflict issue: the gradients of different sub-networks conflict with that of the supernet more severely in ViTs than CNNs, which leads to early saturation in training and inferior convergence.
Ranked #7 on
Neural Architecture Search
on ImageNet
Searching for Two-Stream Models in Multivariate Space for Video Recognition
We design a multivariate search space, including 6 search variables to capture a wide variety of choices in designing two-stream models.
Understanding and Accelerating Neural Architecture Search with Training-Free and Theory-Grounded Metrics
This work targets designing a principled and unified training-free framework for Neural Architecture Search (NAS), with high performance, low cost, and in-depth interpretation.
Multiscale Vision Transformers
We evaluate this fundamental architectural prior for modeling the dense nature of visual signals for a variety of video recognition tasks where it outperforms concurrent vision transformers that rely on large scale external pre-training and are 5-10x more costly in computation and parameters.
Ranked #14 on
Action Classification
on Charades
Visual Transformers: Where Do Transformers Really Belong in Vision Models?
A recent trend in computer vision is to replace convolutions with transformers.
FP-NAS: Fast Probabilistic Neural Architecture Search
Furthermore, to search fast in the multi-variate space, we propose a coarse-to-fine strategy by using a factorized distribution at the beginning which can reduce the number of architecture parameters by over an order of magnitude.
Visual Transformers: Token-based Image Representation and Processing for Computer Vision
In this work, we challenge this paradigm by (a) representing images as semantic visual tokens and (b) running transformers to densely model token relationships.
Decoupling Representation and Classifier for Long-Tailed Recognition
The long-tail distribution of the visual world poses great challenges for deep learning based classification models on how to handle the class imbalance problem.
Ranked #3 on
Long-tail learning with class descriptors
on CUB-LT
Only Time Can Tell: Discovering Temporal Data for Temporal Modeling
However, in current video datasets it has been observed that action classes can often be recognized without any temporal information from a single frame of video.
Drop an Octave: Reducing Spatial Redundancy in Convolutional Neural Networks with Octave Convolution
Similarly, the output feature maps of a convolution layer can also be seen as a mixture of information at different frequencies.
Ranked #147 on
Action Classification
on Kinetics-400
DMC-Net: Generating Discriminative Motion Cues for Fast Compressed Video Action Recognition
Motion has shown to be useful for video understanding, where motion is typically represented by optical flow.
Ranked #1 on
Action Recognition
on UCF-101
Graph-Based Global Reasoning Networks
In this work, we propose a new approach for reasoning globally in which a set of features are globally aggregated over the coordinate space and then projected to an interaction space where relational reasoning can be efficiently computed.
HACS: Human Action Clips and Segments Dataset for Recognition and Temporal Localization
This paper presents a new large-scale dataset for recognition and temporal localization of human actions collected from Web videos.
Ranked #10 on
Temporal Action Localization
on HACS
Learning Concept Taxonomies from Multi-modal Data
We study the problem of automatically building hypernym taxonomies from textual and visual data.
Combining the Best of Convolutional Layers and Recurrent Layers: A Hybrid Network for Semantic Segmentation
State-of-the-art results of semantic segmentation are established by Fully Convolutional neural Networks (FCNs).
HD-CNN: Hierarchical Deep Convolutional Neural Networks for Large Scale Visual Recognition
In this paper, we introduce hierarchical deep CNNs (HD-CNNs) by embedding deep CNNs into a category hierarchy.
Automatic Photo Adjustment Using Deep Neural Networks
Many photographic styles rely on subtle adjustments that depend on the image content and even its semantics.
HD-CNN: Hierarchical Deep Convolutional Neural Network for Large Scale Visual Recognition
In this paper, we introduce hierarchical deep CNNs (HD-CNNs) by embedding deep CNNs into a category hierarchy.
Ranked #174 on
Image Classification
on CIFAR-100
