Search Results for author:
Found 12 papers, 3 papers with code
Spherical Linear Interpolation and Text-Anchoring for Zero-shot Composed Image Retrieval
However, we conjecture that this approach has a downside: the projection module distorts the original image representation and confines the resulting composed embeddings to the text-side.
MA-LMM: Memory-Augmented Large Multimodal Model for Long-Term Video Understanding
However, existing LLM-based large multimodal models (e. g., Video-LLaMA, VideoChat) can only take in a limited number of frames for short video understanding.
Ranked #2 on
Video Classification
on COIN
Universal Pyramid Adversarial Training for Improved ViT Performance
Recently, Pyramid Adversarial training (Herrmann et al., 2022) has been shown to be very effective for improving clean accuracy and distribution-shift robustness of vision transformers.
Revisiting Kernel Temporal Segmentation as an Adaptive Tokenizer for Long-form Video Understanding
While most modern video understanding models operate on short-range clips, real-world videos are often several minutes long with semantically consistent segments of variable length.
Open Vocabulary Semantic Segmentation with Patch Aligned Contrastive Learning
We introduce Patch Aligned Contrastive Learning (PACL), a modified compatibility function for CLIP's contrastive loss, intending to train an alignment between the patch tokens of the vision encoder and the CLS token of the text encoder.
Unifying Tracking and Image-Video Object Detection
We propose TrIVD (Tracking and Image-Video Detection), the first framework that unifies image OD, video OD, and MOT within one end-to-end model.
Raising the Bar on the Evaluation of Out-of-Distribution Detection
In this paper, we define 2 categories of OoD data using the subtly different concepts of perceptual/visual and semantic similarity to in-distribution (iD) data.
Object-Centric Unsupervised Image Captioning
Our work in this paper overcomes this by harvesting objects corresponding to a given sentence from the training set, even if they don't belong to the same image.
MixNorm: Test-Time Adaptation Through Online Normalization Estimation
We present a simple and effective way to estimate the batch-norm statistics during test time, to fast adapt a source model to target test samples.
Differential Motion Evolution for Fine-Grained Motion Deformation in Unsupervised Image Animation
Key findings are twofold: (1) by capturing the motion transfer with an ordinary differential equation (ODE), it helps to regularize the motion field, and (2) by utilizing the source image itself, we are able to inpaint occluded/missing regions arising from large motion changes.
Testing-Time Adaptation through Online Normalization Estimation
We present a simple and effective way to estimate the batch-norm statistics during test time, to fast adapt a source model to target test samples.
Fast Adaptive Anomaly Detection
Anything outside of a given normal population is by definition an anomaly.
