Search Results for author:
Found 16 papers, 8 papers with code
M2D2M: Multi-Motion Generation from Text with Discrete Diffusion Models
We introduce the Multi-Motion Discrete Diffusion Models (M2D2M), a novel approach for human motion generation from textual descriptions of multiple actions, utilizing the strengths of discrete diffusion models.
Follow the Rules: Reasoning for Video Anomaly Detection with Large Language Models
In the induction stage, the LLM is fed with few-shot normal reference samples and then summarizes these normal patterns to induce a set of rules for detecting anomalies.
Ranked #2 on
Video Anomaly Detection
on UBnormal
Can't make an Omelette without Breaking some Eggs: Plausible Action Anticipation using Large Video-Language Models
To address this limitation, we explore the generative capability of a large video-language model in our work and further, develop the understanding of plausibility in an action sequence by introducing two objective functions, a counterfactual-based plausible action sequence learning loss and a long-horizon action repetition loss.
Ranked #1 on
Action Anticipation
on EPIC-KITCHENS-100
Uncertainty-aware Action Decoupling Transformer for Action Anticipation
The objective is to make the two decoupled tasks assist each other and eventually improve the action anticipation task.
Ranked #1 on
Action Anticipation
on 50-Salads
Vamos: Versatile Action Models for Video Understanding
To interpret the important text evidence for question answering, we generalize the concept bottleneck model to work with tokens and nonlinear models, which uses hard attention to select a small subset of tokens from the free-form text as inputs to the LLM reasoner.
Object-centric Video Representation for Long-term Action Anticipation
To recognize and predict human-object interactions, we use a Transformer-based neural architecture which allows the "retrieval" of relevant objects for action anticipation at various time scales.
Ranked #4 on
Long Term Action Anticipation
on Ego4D
ViCor: Bridging Visual Understanding and Commonsense Reasoning with Large Language Models
For problems where the goal is to infer conclusions beyond image content, which we noted as visual commonsense inference (VCI), VLMs face difficulties, while LLMs, given sufficient visual evidence, can use commonsense to infer the answer well.
AntGPT: Can Large Language Models Help Long-term Action Anticipation from Videos?
We propose to formulate the LTA task from two perspectives: a bottom-up approach that predicts the next actions autoregressively by modeling temporal dynamics; and a top-down approach that infers the goal of the actor and plans the needed procedure to accomplish the goal.
Ranked #2 on
Long Term Action Anticipation
on Ego4D
AdamsFormer for Spatial Action Localization in the Future
SALF is challenging because it requires understanding the underlying physics of video observations to predict future action locations accurately.
ViTGAN: Training GANs with Vision Transformers
Recently, Vision Transformers (ViTs) have shown competitive performance on image recognition while requiring less vision-specific inductive biases.
Ranked #76 on
Image Generation
on CIFAR-10
Dual Contradistinctive Generative Autoencoder
Our model, named dual contradistinctive generative autoencoder (DC-VAE), integrates an instance-level discriminative loss (maintaining the instance-level fidelity for the reconstruction/synthesis) with a set-level adversarial loss (encouraging the set-level fidelity for there construction/synthesis), both being contradistinctive.
Ranked #2 on
Image Generation
on LSUN Bedroom 128 x 128
Unaligned Image-to-Sequence Transformation with Loop Consistency
We tackle the problem of modeling sequential visual phenomena.
Learning Instance Occlusion for Panoptic Segmentation
Panoptic segmentation requires segments of both "things" (countable object instances) and "stuff" (uncountable and amorphous regions) within a single output.
Ranked #22 on
Panoptic Segmentation
on COCO test-dev
Meta-Learning with Differentiable Convex Optimization
We propose to use these predictors as base learners to learn representations for few-shot learning and show they offer better tradeoffs between feature size and performance across a range of few-shot recognition benchmarks.
Ranked #12 on
Few-Shot Image Classification
on FC100 5-way (1-shot)
Controllable Top-down Feature Transformer
We study the intrinsic transformation of feature maps across convolutional network layers with explicit top-down control.
Wasserstein Introspective Neural Networks
We present Wasserstein introspective neural networks (WINN) that are both a generator and a discriminator within a single model.
