Search Results for author:
Found 37 papers, 7 papers with code
Incorporating Geo-Diverse Knowledge into Prompting for Increased Geographical Robustness in Object Recognition
In the absence of training data from target geographies, we hypothesize that geographically diverse descriptive knowledge of categories can enhance robustness.
Semi-Supervised Domain Generalization for Object Detection via Language-Guided Feature Alignment
Existing domain adaptation (DA) and generalization (DG) methods in object detection enforce feature alignment in the visual space but face challenges like object appearance variability and scene complexity, which make it difficult to distinguish between objects and achieve accurate detection.
Ranked #1 on
Domain Generalization
on Watercolor2k
Impact of Experiencing Misrecognition by Teachable Agents on Learning and Rapport
While speech-enabled teachable agents have some advantages over typing-based ones, they are vulnerable to errors stemming from misrecognition by automatic speech recognition (ASR).
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Hypernymization of named entity-rich captions for grounding-based multi-modal pretraining
In this work, we investigate hypernymization as a way to deal with named entities for pretraining grounding-based multi-modal models and for fine-tuning on open-vocabulary detection.
Boosting Weakly Supervised Object Detection using Fusion and Priors from Hallucinated Depth
We propose an amplifier method for enhancing the performance of WSOD by integrating depth information.
Investigating the Role of Attribute Context in Vision-Language Models for Object Recognition and Detection
Methods are mostly evaluated in terms of how well object class names are learned, but captions also contain rich attribute context that should be considered when learning object alignment.
VEIL: Vetting Extracted Image Labels from In-the-Wild Captions for Weakly-Supervised Object Detection
The use of large-scale vision-language datasets is limited for object detection due to the negative impact of label noise on localization.
Weakly-Supervised HOI Detection from Interaction Labels Only and Language/Vision-Language Priors
In this paper, we tackle HOI detection with the weakest supervision setting in the literature, using only image-level interaction labels, with the help of a pretrained vision-language model (VLM) and a large language model (LLM).
Contrastive View Design Strategies to Enhance Robustness to Domain Shifts in Downstream Object Detection
To address this gap, we conduct an empirical study of contrastive learning and out-of-domain object detection, studying how contrastive view design affects robustness.
Comparison of Lexical Alignment with a Teachable Robot in Human-Robot and Human-Human-Robot Interactions
Speakers build rapport in the process of aligning conversational behaviors with each other.
Emphasizing Complementary Samples for Non-literal Cross-modal Retrieval
Existing cross-modal retrieval methods assume a straightforward relationship where images and text contain portrayals or mentions of the same objects.
Ranked #1 on
Cross-Modal Retrieval
on COCO 2014
(using extra training data)
Symbolic image detection using scene and knowledge graphs
In this paper, we use a scene graph, a graph representation of an image, to capture visual components.
Weakly-Supervised Action Detection Guided by Audio Narration
We explored how to eliminate the expensive annotations in video detection data which provide refined boundaries.
Learning Better Visual Representations for Weakly-Supervised Object Detection Using Natural Language Supervision
We present a framework to better leverage natural language supervision for a specific downstream task, namely weakly-supervised object detection (WSOD).
Exploring Corruption Robustness: Inductive Biases in Vision Transformers and MLP-Mixers
We find that vision transformer architectures are inherently more robust to corruptions than the ResNet-50 and MLP-Mixers.
Linguistic Structures as Weak Supervision for Visual Scene Graph Generation
Prior work in scene graph generation requires categorical supervision at the level of triplets - subjects and objects, and predicates that relate them, either with or without bounding box information.
BasisNet: Two-stage Model Synthesis for Efficient Inference
With early termination, the average cost can be further reduced to 198M MAdds while maintaining accuracy of 80. 0% on ImageNet.
Ranked #661 on
Image Classification
on ImageNet
Domain-robust VQA with diverse datasets and methods but no target labels
The observation that computer vision methods overfit to dataset specifics has inspired diverse attempts to make object recognition models robust to domain shifts.
SpotPatch: Parameter-Efficient Transfer Learning for Mobile Object Detection
In this paper we address the question: can task-specific detectors be trained and represented as a shared set of weights, plus a very small set of additional weights for each task?
Detecting Persuasive Atypicality by Modeling Contextual Compatibility
We propose a new approach to detect atypicality in persuasive imagery.
Learning to Transfer Visual Effects from Videos to Images
We study the problem of animating images by transferring spatio-temporal visual effects (such as melting) from a collection of videos.
Preserving Semantic Neighborhoods for Robust Cross-modal Retrieval
The abundance of multimodal data (e. g. social media posts) has inspired interest in cross-modal retrieval methods.
Predicting the Politics of an Image Using Webly Supervised Data
We collect a dataset of over one million unique images and associated news articles from left- and right-leaning news sources, and develop a method to predict the image's political leaning.
Cap2Det: Learning to Amplify Weak Caption Supervision for Object Detection
Learning to localize and name object instances is a fundamental problem in vision, but state-of-the-art approaches rely on expensive bounding box supervision.
Measuring Effectiveness of Video Advertisements
They are attractive to companies and nearly unavoidable for consumers.
Artistic Object Recognition by Unsupervised Style Adaptation
To do so, we introduce a complementary training modality constructed to be similar in artistic style to the target domain, and enforce that the network learns features that are invariant between the two training modalities.
Learning to discover and localize visual objects with open vocabulary
To alleviate the cost of obtaining accurate bounding boxes for training today's state-of-the-art object detection models, recent weakly supervised detection work has proposed techniques to learn from image-level labels.
Story Understanding in Video Advertisements
We dedicate our study to understand the dynamic structure of video ads automatically.
Persuasive Faces: Generating Faces in Advertisements
We show how our model can be used to produce visually distinct faces which appear to be from a fixed ad topic category.
Equal But Not The Same: Understanding the Implicit Relationship Between Persuasive Images and Text
Images and text in advertisements interact in complex, non-literal ways.
Image Retrieval with Mixed Initiative and Multimodal Feedback
How would you search for a unique, fashionable shoe that a friend wore and you want to buy, but you didn't take a picture?
ADVISE: Symbolism and External Knowledge for Decoding Advertisements
In order to convey the most content in their limited space, advertisements embed references to outside knowledge via symbolism.
Automatic Understanding of Image and Video Advertisements
There is more to images than their objective physical content: for example, advertisements are created to persuade a viewer to take a certain action.
Crowdsourcing in Computer Vision
Computer vision systems require large amounts of manually annotated data to properly learn challenging visual concepts.
Seeing Behind the Camera: Identifying the Authorship of a Photograph
To explore the feasibility of current computer vision techniques to address this problem, we created a new dataset of over 180, 000 images taken by 41 well-known photographers.
Discovering Attribute Shades of Meaning with the Crowd
We propose to discover shades of attribute meaning.
WhittleSearch: Interactive Image Search with Relative Attribute Feedback
We propose a novel mode of feedback for image search, where a user describes which properties of exemplar images should be adjusted in order to more closely match his/her mental model of the image sought.
