Search Results for author:
Found 17 papers, 2 papers with code
Representation Reliability and Its Impact on Downstream Tasks
Self-supervised pre-trained models extract general-purpose representations from data, and quantifying how reliable they are is crucial because many downstream models use these representations as input for their own tasks.
LLM2Loss: Leveraging Language Models for Explainable Model Diagnostics
We then extract a semantically meaningful representation for each training data point (such as CLIP embeddings from its visual encoder) and train a lightweight diagnosis model which maps this semantically meaningful representation of a data point to its task loss.
Improving Identity-Robustness for Face Models
When it comes to models directly trained on human faces, a sensitive confounder is that of human identities.
Fairness via Adversarial Attribute Neighbourhood Robust Learning
Improving fairness between privileged and less-privileged sensitive attribute groups (e. g, {race, gender}) has attracted lots of attention.
Uncertainty in Contrastive Learning: On the Predictability of Downstream Performance
In this work, we study whether the uncertainty of such a representation can be quantified for a single datapoint in a meaningful way.
On Negative Sampling for Audio-Visual Contrastive Learning from Movies
The abundance and ease of utilizing sound, along with the fact that auditory clues reveal a plethora of information about what happens in a scene, make the audio-visual space an intuitive choice for representation learning.
Character-focused Video Thumbnail Retrieval
Prominence and interactions: Character(s) in the thumbnail should be important character(s) in the video, to prevent the algorithm from suggesting non-representative frames as candidates.
Estimating Structural Disparities for Face Models
Performance of the model for each group is calculated by comparing $\hat{y}$ and $y$ for the datapoints within a specific group, and as a result, disparity of performance across the different groups can be calculated.
On Attention Modules for Audio-Visual Synchronization
To judge whether audio and video signals of a multimedia presentation are synchronized, we as humans often pay close attention to discriminative spatio-temporal blocks of the video (e. g. synchronizing the lip movement with the utterance of words, or the sound of a bouncing ball at the moment it hits the ground).
From Third Person to First Person: Dataset and Baselines for Synthesis and Retrieval
In this work, we introduce two datasets (synthetic and natural/real) containing simultaneously recorded egocentric and exocentric videos.
Integrating Egocentric Videos in Top-view Surveillance Videos: Joint Identification and Temporal Alignment
Videos recorded from first person (egocentric) perspective have little visual appearance in common with those from third person perspective, especially with videos captured by top-view surveillance cameras.
EgoReID: Cross-view Self-Identification and Human Re-identification in Egocentric and Surveillance Videos
Human identification remains to be one of the challenging tasks in computer vision community due to drastic changes in visual features across different viewpoints, lighting conditions, occlusion, etc.
EgoTransfer: Transferring Motion Across Egocentric and Exocentric Domains using Deep Neural Networks
On one hand, the abundance of egocentric cameras in the past few years has offered the opportunity to study a lot of vision problems from the first-person perspective.
Egocentric Meets Top-view
First, having a set of egocentric videos and a top-view video, can we verify if the top-view video contains all, or some of the egocentric viewers present in the egocentric set?
Ego2Top: Matching Viewers in Egocentric and Top-view Videos
At the same time, surveillance cameras and drones offer an abundance of visual information, often captured from top-view.
Geo-Semantic Segmentation
In this paper, we propose a method which leverages information acquired from GIS databases to perform semantic segmentation of the image alongside with geo-referencing each semantic segment with its address and geo-location.
GPS-Tag Refinement using Random Walks with an Adaptive Damping Factor
We develop a robust method for identification and refinement of this subset using the rest of the images in the dataset.
