Related papers: Phrase Grounding by Soft-Label Chain Conditional R…
We present LS-CRF, a new method for very efficient large-scale training of Conditional Random Fields (CRFs). It is inspired by existing closed-form expressions for the maximum likelihood parameters of a generative graphical model with tree…
The paper presents an approach to semantic grounding of language models (LMs) that conceptualizes the LM as a conditional model generating text given a desired semantic message formalized as a set of entity-relationship triples. It embeds…
Conditional Random Field (CRF) based neural models are among the most performant methods for solving sequence labeling problems. Despite its great success, CRF has the shortcoming of occasionally generating illegal sequences of tags, e.g.…
This paper presents a method of designing specific high-order dependency factor on the linear chain conditional random fields (CRFs) for named entity recognition (NER). Named entities tend to be separated from each other by multiple outside…
Neural approaches to sequence labeling often use a Conditional Random Field (CRF) to model their output dependencies, while Recurrent Neural Networks (RNN) are used for the same purpose in other tasks. We set out to establish RNNs as an…
Video captioning generate a sentence that describes the video content. Existing methods always require a number of captions (\eg, 10 or 20) per video to train the model, which is quite costly. In this work, we explore the possibility of…
This paper presents an empirical study of two widely-used sequence prediction models, Conditional Random Fields (CRFs) and Long Short-Term Memory Networks (LSTMs), on two fundamental tasks for Vietnamese text processing, including…
Persuasion aims at forming one's opinion and action via a series of persuasive messages containing persuader's strategies. Due to its potential application in persuasive dialogue systems, the task of persuasive strategy recognition has…
Conditional Random Fields (CRFs) are undirected graphical models, a special case of which correspond to conditionally-trained finite state machines. A key advantage of these models is their great flexibility to include a wide array of…
A robot's ability to understand or ground natural language instructions is fundamentally tied to its knowledge about the surrounding world. We present an approach to grounding natural language utterances in the context of factual…
Language-aligned vision foundation models perform strongly across diverse downstream tasks. Yet, their learned representations remain opaque, making interpreting their decision-making difficult. Recent work decompose these representations…
The key to successful grounding for video surveillance is to understand a semantic phrase corresponding to important actors and objects. Conventional methods ignore comprehensive contexts for the phrase or require heavy computation for…
Reasoning segmentation requires models to ground complex, implicit textual queries into precise pixel-level masks. Existing approaches rely on a single segmentation token $\texttt{<SEG>}$, whose hidden state implicitly encodes both semantic…
Superpixel-based Higher-order Conditional Random Fields (CRFs) are effective in enforcing long-range consistency in pixel-wise labeling problems, such as semantic segmentation. However, their major short coming is considerably longer time…
Given an input image, and nothing else, our method returns the bounding boxes of objects in the image and phrases that describe the objects. This is achieved within an open world paradigm, in which the objects in the input image may not…
We consider two models for the sequence labeling (tagging) problem. The first one is a {\em Pattern-Based Conditional Random Field }(\PB), in which the energy of a string (chain labeling) $x=x_1\ldots x_n\in D^n$ is a sum of terms over…
A conditional random field (CRF) model for cloud detection in ground based sky images is presented. We show that very high cloud detection accuracy can be achieved by combining a discriminative classifier and a higher order clique potential…
Phrase grounding, i.e., mapping natural language phrases to specific image regions, holds significant potential for disease localization in medical imaging through clinical reports. While current state-of-the-art methods rely on…
Modern semantic segmentation methods devote much effect to adjusting image feature representations to improve the segmentation performance in various ways, such as architecture design, attention mechnism, etc. However, almost all those…
Significant progress has been made in recent years in image captioning, an active topic in the fields of vision and language. However, existing methods tend to yield overly general captions and consist of some of the most frequent…