Related papers: Zero-Shot Contextual Embeddings via Offline Synthe…
Generalized zero-shot learning(GZSL) aims to classify samples from seen and unseen labels, assuming unseen labels are not accessible during training. Recent advancements in GZSL have been expedited by incorporating…
Semantic parsing plays a key role in digital voice assistants such as Alexa, Siri, and Google Assistant by mapping natural language to structured meaning representations. When we want to improve the capabilities of a voice assistant by…
We study the zero-shot Composed Image Retrieval (ZS-CIR) task, which is to retrieve the target image given a reference image and a description without training on the triplet datasets. Previous works generate pseudo-word tokens by…
Language models can be viewed as functions that embed text into Euclidean space, where the quality of the embedding vectors directly determines model performance, training such neural networks involves various uncertainties. This paper…
Automatic art analysis aims to classify and retrieve artistic representations from a collection of images by using computer vision and machine learning techniques. In this work, we propose to enhance visual representations from neural…
Recent text-to-image diffusion models have significantly improved visual quality and text alignment. However, generating a sequence of images while preserving consistent character identity across diverse scene descriptions remains a…
Compression-based dissimilarities (CD) offer a flexible and domain-agnostic means of measuring similarity by identifying implicit information through redundancies between data objects. However, as similarity features are derived from the…
This paper investigates the problem of learning cross-lingual representations in a contextual space. We propose Cross-Lingual BERT Transformation (CLBT), a simple and efficient approach to generate cross-lingual contextualized word…
Compositional zero-shot learning (CZSL) aims to recognize unseen compositions with prior knowledge of known primitives (attribute and object). Previous works for CZSL often suffer from grasping the contextuality between attribute and…
Unsupervised Domain Adaptation (UDA) is a critical challenge in real-world vision systems, especially in resource-constrained environments like drones, where memory and computation are limited. Existing prompt-driven UDA methods typically…
Zero-shot learning (ZSL) makes object recognition in images possible in absence of visual training data for a part of the classes from a dataset. When the number of classes is large, classes are usually represented by semantic class…
Recent years have seen a growth in user-centric applications that require effective knowledge transfer across tasks in the low-data regime. An example is personalization, where a pretrained system is adapted by learning on small amounts of…
A significant shortcoming of current state-of-the-art (SOTA) named-entity recognition (NER) systems is their lack of generalization to unseen domains, which poses a major problem since obtaining labeled data for NER in a new domain is…
Semantic search of Earth observation archives remains challenging. Visual foundation models such as CLAY produce rich embeddings of satellite imagery but lack the natural-language grounding needed for intuitive query, and full contrastive…
We propose Grounded Adaptation for Zero-shot Executable Semantic Parsing (GAZP) to adapt an existing semantic parser to new environments (e.g. new database schemas). GAZP combines a forward semantic parser with a backward utterance…
We introduce a new task, Contextual Text Style Transfer - translating a sentence into a desired style with its surrounding context taken into account. This brings two key challenges to existing style transfer approaches: ($i$) how to…
Video anomalies often depend on contextual information available and temporal evolution. Non-anomalous action in one context can be anomalous in some other context. Most anomaly detectors, however, do not notice this type of context, which…
Large pre-trained vision-language models have shown great prominence in transferring pre-acquired knowledge to various domains and downstream tasks with appropriate prompting or tuning. Existing prevalent tuning methods can be generally…
This paper proposes a novel Zero-Shot Action Recognition~(ZSAR) method based on contrastive learning. In ZSAR, we aim to classify examples from classes that were missing during training. Two well-known problems remain in ZSAR: the semantic…
We propose a novel setting for learning, where the input domain is the image of a map defined on the product of two sets, one of which completely determines the labels. We derive a new risk bound for this setting that decomposes into a bias…