waybarrios
commited on
Commit
•
12b7bad
1
Parent(s):
2daec48
Create README.md
Browse files
README.md
ADDED
@@ -0,0 +1,187 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- grounding
|
4 |
+
- video
|
5 |
+
- understanding
|
6 |
+
- multimodal
|
7 |
+
- MAD
|
8 |
+
- long video
|
9 |
+
- moments
|
10 |
+
- moment retrieval
|
11 |
+
license: bsd
|
12 |
+
language:
|
13 |
+
- en
|
14 |
+
metrics:
|
15 |
+
- recall
|
16 |
+
pipeline_tag: text-to-video
|
17 |
+
---
|
18 |
+
# Guidance Based Video Grounding.
|
19 |
+
|
20 |
+
The official implementation of the paper: ["Localizing Moments in Long Video Via Multimodal Guidance"](https://arxiv.org/abs/2302.13372). In this repository,
|
21 |
+
we provide the predicted scores from the Guidance Model using [MAD Dataset](https://github.com/Soldelli/MAD).
|
22 |
+
|
23 |
+
## Citation
|
24 |
+
If you find this implementation useful in your research, please use the following BibTeX entry for citation:
|
25 |
+
```
|
26 |
+
@article{Barrios2023LocalizingMI,
|
27 |
+
title={Localizing Moments in Long Video Via Multimodal Guidance},
|
28 |
+
author={Wayner Barrios and Mattia Soldan and Fabian Caba Heilbron and Alberto M. Ceballos-Arroyo and Bernard Ghanem},
|
29 |
+
journal={ArXiv},
|
30 |
+
year={2023},
|
31 |
+
volume={abs/2302.13372}
|
32 |
+
}
|
33 |
+
```
|
34 |
+
|
35 |
+
## Prediction Zoo.
|
36 |
+
|
37 |
+
The provided predictions correspond to the scores generated by the Guidance model using sliding windows of 64 frames and 128 frames in length. The predictions are stored in a pickle object with the following structure:
|
38 |
+
```python
|
39 |
+
In [1]: import pickle
|
40 |
+
In [2]: with open("guidance_scores_MAD_test_128.pkl",'rb') as f:
|
41 |
+
...: scores = pickle.load(f)
|
42 |
+
In [3]: len(scores)
|
43 |
+
Out[3]: 72044
|
44 |
+
In [4]: scores[0].keys()
|
45 |
+
Out[4]: dict_keys(['qid', 'vid', 'windows', 'score'])
|
46 |
+
```
|
47 |
+
```python
|
48 |
+
{ 'qid': '0',
|
49 |
+
'score': array([1.48404761e-05, 1.40372722e-05, 1.46572347e-05, 1.28814381e-05,
|
50 |
+
1.34291167e-05, 1.32850864e-05, 1.61252574e-05, 6.24697859e-05,
|
51 |
+
4.70118430e-05, 1.63803907e-05, 2.77301951e-05, 2.59740209e-05,
|
52 |
+
9.86061990e-01, 4.11081433e-01, 1.71889886e-02, 1.37453452e-01,
|
53 |
+
1.75393507e-05, 1.92647931e-05, 5.38236709e-05, 6.90551009e-04,
|
54 |
+
7.63237834e-01, 9.73204970e-02, 1.73201097e-05, 2.48163269e-05,
|
55 |
+
5.99260893e-05, 1.84824003e-05, 2.14560350e-05, 1.04043145e-04,
|
56 |
+
5.24206553e-05, 1.88337926e-05, 1.62523775e-05, 1.23760619e-05,
|
57 |
+
1.15747998e-05, 1.85713252e-05, 3.93810224e-05, 4.38277610e-04,
|
58 |
+
4.63226315e-05, 2.76185543e-04, 6.71112502e-05, 2.05889755e-05,
|
59 |
+
5.27229131e-05, 4.56629896e-05, 2.62997986e-04, 1.23860036e-05,
|
60 |
+
1.19574897e-05, 1.27713274e-05, 1.34036281e-05, 1.49246125e-05,
|
61 |
+
1.66437039e-05, 1.32685755e-05, 1.36442995e-05, 1.39407657e-05,
|
62 |
+
9.44265649e-02, 5.19266985e-02, 3.09179362e-04, 1.66565824e-05,
|
63 |
+
1.52278981e-05, 1.34415832e-05, 1.16731699e-05, 1.19617898e-05,
|
64 |
+
1.34421471e-05, 1.35606424e-05, 1.40685788e-05, 1.44712585e-05,
|
65 |
+
1.49164434e-05, 1.32006107e-05, 1.23232739e-05, 1.22480678e-05,
|
66 |
+
1.36934423e-05, 8.42598165e-05, 1.90059054e-05, 1.52820303e-05,
|
67 |
+
1.25335091e-05, 1.30556955e-05, 1.18760063e-05, 1.14885261e-05,
|
68 |
+
1.17362497e-05, 1.12321404e-05, 1.24243248e-04, 1.45946506e-05,
|
69 |
+
4.47804232e-05, 1.39249141e-05, 1.34848015e-05, 3.25621368e-05,
|
70 |
+
1.44184843e-01, 2.68866897e-05, 1.92906227e-05, 1.76019021e-05,
|
71 |
+
1.58657276e-05, 1.28230713e-05, 1.28012252e-05, 1.29981381e-05,
|
72 |
+
1.67807830e-05, 1.70492331e-05, 1.40562279e-05, 1.61650114e-05,
|
73 |
+
1.47591518e-05, 1.63778402e-02, 1.42061428e-04, 6.93475548e-03,
|
74 |
+
6.02264590e-05, 8.72147648e-05, 9.83794928e-01, 9.91553962e-01,
|
75 |
+
9.63991106e-01, 8.97689939e-01, 1.28758256e-04, 2.88744595e-05,
|
76 |
+
1.70378244e-05, 2.29878224e-05, 2.43768354e-05, 1.59022475e-05,
|
77 |
+
1.30911794e-05, 1.81753130e-05, 2.05728411e-05, 1.25869919e-05,
|
78 |
+
1.25580364e-05, 1.16062802e-05, 1.37536981e-05, 1.34730390e-05,
|
79 |
+
1.40373795e-05, 1.33059066e-05, 1.30285189e-05, 1.37811385e-05,
|
80 |
+
2.23064744e-05, 1.44057722e-05, 1.42116378e-05, 1.93661017e-05,
|
81 |
+
1.58555758e-05, 1.43071402e-05, 1.38224150e-05, 1.28803194e-05,
|
82 |
+
1.20950817e-05, 1.41009232e-05, 1.45958602e-05, 1.23285527e-05,
|
83 |
+
1.38767664e-05, 1.59005958e-05, 1.49218240e-05, 1.21883040e-05,
|
84 |
+
1.24096860e-05, 1.63976423e-04, 3.71323113e-05, 1.49581110e-05,
|
85 |
+
1.28865731e-05, 8.20189889e-05, 1.94104978e-05, 1.45575204e-05,
|
86 |
+
1.19119395e-05, 1.17359577e-05, 1.33997301e-05, 1.31552797e-05,
|
87 |
+
1.29547625e-05, 1.46081702e-05, 1.37864763e-05, 2.89076870e-05,
|
88 |
+
2.40834688e-05, 2.44160365e-05, 3.74382762e-05, 4.72434871e-02,
|
89 |
+
1.53820711e-05, 1.25494762e-05, 1.16858791e-05, 1.33582507e-05,
|
90 |
+
6.86281201e-05, 1.72452001e-05, 1.32617952e-05, 1.24350836e-05,
|
91 |
+
1.32563446e-05, 1.50281312e-05, 2.07685662e-05, 3.12883203e-05,
|
92 |
+
5.31642836e-05, 7.05183193e-05, 1.51949525e-05, 1.41901855e-05,
|
93 |
+
1.51822069e-05, 3.32951342e-04, 8.94680124e-05, 1.65749607e-05,
|
94 |
+
2.18829446e-05, 2.16037024e-05, 1.89978218e-05, 4.97834710e-03,
|
95 |
+
2.03153506e-01, 1.54585496e-03, 1.23195614e-05, 1.28703259e-05,
|
96 |
+
1.51874347e-05, 1.30843009e-05, 1.32952518e-05, 1.83968314e-05,
|
97 |
+
3.42841486e-05, 9.24622072e-05, 1.33280428e-05, 1.38418063e-05,
|
98 |
+
1.52235261e-05, 1.41796754e-05, 1.46450093e-05, 2.20195379e-05,
|
99 |
+
1.83107302e-04, 1.82420099e-05, 1.50840988e-05, 1.33859876e-05,
|
100 |
+
1.51073200e-05, 1.47391929e-05, 1.49910848e-05, 1.53916826e-05,
|
101 |
+
1.31657725e-05, 1.38312898e-05, 1.90024621e-05, 1.58155744e-05,
|
102 |
+
1.31786610e-05, 1.57141967e-05, 1.65828824e-05, 1.46924167e-05,
|
103 |
+
1.38433634e-05, 5.21887268e-05, 2.85502132e-02, 2.30753481e-01,
|
104 |
+
7.06195598e-04, 1.50714346e-04, 1.27303065e-03, 1.33986650e-02,
|
105 |
+
7.64285505e-04, 2.07327234e-04, 6.83149046e-05, 3.26294066e-05,
|
106 |
+
3.00217052e-05, 3.59058060e-04, 1.75943842e-05, 4.50351909e-05,
|
107 |
+
6.54372343e-05, 7.06970895e-05, 3.67312983e-04, 1.05719395e-01,
|
108 |
+
4.43235294e-05, 2.82063011e-05, 7.51458792e-05, 1.61291231e-04,
|
109 |
+
4.26617444e-05, 8.98458238e-05, 5.37320266e-05, 7.81280905e-05,
|
110 |
+
4.74652685e-02, 6.73964678e-04, 7.80265400e-05, 2.98924297e-05,
|
111 |
+
4.71418061e-05, 9.99735785e-05, 5.41929447e-04, 8.76590490e-01,
|
112 |
+
7.32870936e-01, 9.47873652e-01, 9.83479261e-01, 9.41197515e-01,
|
113 |
+
3.02340268e-05, 5.52863061e-01, 4.90591303e-02, 5.52392844e-03,
|
114 |
+
1.66527767e-04, 6.01128559e-05, 2.75078182e-05, 5.36037696e-05,
|
115 |
+
2.72706511e-05, 5.20218709e-05, 1.74067172e-04, 9.59624112e-01,
|
116 |
+
9.92105484e-01, 6.41801059e-01, 7.50956178e-01, 1.66324535e-05,
|
117 |
+
1.36247700e-05, 1.38954510e-05, 1.32978639e-05, 2.76602568e-05,
|
118 |
+
8.64359558e-01, 2.82314628e-01, 6.86250278e-04, 1.61339794e-05,
|
119 |
+
1.76240802e-01, 6.14342950e-02, 1.79430062e-05, 1.85770459e-05,
|
120 |
+
2.49132900e-05, 4.90641105e-05, 1.38329369e-05, 1.35371911e-05,
|
121 |
+
1.19879533e-05, 1.28572465e-05, 1.49452917e-05, 1.34064794e-05,
|
122 |
+
1.20641280e-05, 1.38642654e-05, 1.28597740e-05, 1.21135636e-05,
|
123 |
+
1.19547185e-05, 1.27106450e-05, 1.24800990e-05, 1.45651029e-05,
|
124 |
+
1.51306494e-05, 1.31757206e-05, 1.44625528e-05, 2.93072371e-05,
|
125 |
+
1.55961770e-05, 1.38226005e-05, 2.85501122e-01, 9.54893649e-01,
|
126 |
+
4.26807284e-01, 7.88133383e-01, 1.15605462e-05, 1.27675758e-05,
|
127 |
+
1.74503912e-05, 1.22338257e-04, 4.07951375e-05, 6.67655331e-05,
|
128 |
+
2.63322181e-05, 6.43799603e-01, 9.40359533e-01, 8.85976017e-01,
|
129 |
+
4.58170444e-01, 1.68637175e-03, 5.94505800e-05, 9.05500948e-01,
|
130 |
+
3.18567127e-01, 4.67336411e-03, 2.84927974e-05, 3.81192891e-03,
|
131 |
+
4.18508105e-04, 6.88799983e-03, 9.18629944e-01, 8.45510900e-01,
|
132 |
+
1.88187569e-01, 1.15205767e-02, 6.14926934e-01, 9.16110933e-01,
|
133 |
+
3.21912378e-01, 9.68408361e-02, 2.36877706e-03, 3.30457231e-04,
|
134 |
+
9.32341874e-01, 6.69624686e-01, 3.61131132e-02, 4.71764088e-01,
|
135 |
+
3.23702669e-04, 5.40765934e-04, 2.96235172e-04, 1.00755557e-01,
|
136 |
+
2.59187482e-02, 9.91479377e-04, 5.00017107e-02, 9.33302939e-03,
|
137 |
+
8.73835742e-01, 9.06303883e-01, 1.98892485e-02, 2.06603622e-03,
|
138 |
+
2.67300452e-03, 1.63171062e-05, 4.14947972e-05, 2.11949199e-02,
|
139 |
+
5.66720143e-02, 6.37245998e-02, 3.02139521e-01, 4.86139301e-03,
|
140 |
+
6.51149167e-05, 8.24632589e-05, 2.42551632e-05, 2.16892213e-01,
|
141 |
+
9.93161321e-01, 9.07774687e-01, 9.85157251e-01, 7.91489899e-01,
|
142 |
+
6.24064269e-05, 2.82448274e-03, 6.10993884e-05, 4.63459146e-05,
|
143 |
+
6.72110255e-05, 2.53440558e-05, 2.50527592e-05, 4.85404918e-04,
|
144 |
+
7.80891351e-05, 4.56315975e-05, 1.90765320e-04, 8.94685328e-01,
|
145 |
+
9.85134244e-01, 9.36044097e-01, 1.42211165e-05, 1.49489415e-05,
|
146 |
+
1.69001578e-05, 1.66201044e-05, 2.41175085e-01, 5.41068694e-05,
|
147 |
+
1.77346919e-05, 3.90491296e-05, 2.48894852e-04, 1.45345357e-05,
|
148 |
+
1.64555768e-05, 1.53538731e-05, 1.38164451e-05, 1.68559291e-05,
|
149 |
+
3.19991705e-05, 2.60154466e-05, 1.41664159e-05, 1.22337908e-04,
|
150 |
+
4.30386774e-02, 3.52067378e-04, 2.77736799e-05, 1.43605203e-05,
|
151 |
+
1.33721569e-05, 1.43800498e-05, 1.23751524e-05, 2.31819286e-05,
|
152 |
+
9.83208010e-05, 2.08199883e-04, 3.14763274e-05, 3.47468827e-04,
|
153 |
+
1.10434856e-04, 3.18150487e-05, 1.72609471e-05, 2.70375167e-05,
|
154 |
+
1.67231119e-05, 1.80254483e-05, 2.09855771e-05, 1.66565824e-05,
|
155 |
+
1.64901703e-05, 3.01825115e-04, 7.29017615e-01, 1.12410297e-03,
|
156 |
+
6.18876831e-04, 2.08720026e-04, 2.29539564e-05, 1.47635437e-05,
|
157 |
+
4.10786743e-05, 2.57481169e-02, 8.77772836e-05, 4.92439649e-05,
|
158 |
+
9.44633852e-04, 2.61720526e-03, 8.41950595e-01, 8.63339067e-01,
|
159 |
+
5.76047751e-05, 8.71496499e-01, 9.07008648e-01, 8.54207218e-01,
|
160 |
+
3.62060557e-04, 7.98364286e-04, 7.50755966e-02, 3.81207588e-04,
|
161 |
+
6.62766863e-03, 1.50808028e-03, 5.67528963e-01, 7.69607246e-01,
|
162 |
+
4.62092081e-04, 1.82087897e-04, 9.24605787e-01, 9.67480242e-01,
|
163 |
+
3.22210602e-03, 3.38318609e-02, 7.42516349e-05, 2.80661490e-02,
|
164 |
+
7.69108906e-03, 8.99414954e-05, 5.23393810e-01, 7.17914104e-01,
|
165 |
+
5.11704478e-04, 2.06177612e-03, 7.79069304e-01, 1.28432157e-05,
|
166 |
+
1.51723981e-01, 7.02154310e-03, 9.71324384e-01, 8.30839634e-01,
|
167 |
+
6.24295863e-05, 1.97836489e-05, 1.80826428e-05, 1.67380622e-05,
|
168 |
+
1.57646009e-05, 5.96713580e-05, 7.05929342e-05, 2.16401986e-05,
|
169 |
+
1.69063496e-05, 1.36657072e-05, 1.44965925e-05, 2.01106413e-05,
|
170 |
+
1.66287136e-05, 1.51022632e-05, 1.20727018e-05, 1.36815515e-05,
|
171 |
+
1.57434170e-05, 3.38077080e-03, 1.93943546e-04, 1.50704973e-05,
|
172 |
+
1.36058252e-05, 1.23554828e-05, 1.20090635e-05, 1.20484674e-05,
|
173 |
+
1.15330831e-05, 1.24158278e-05, 1.21374187e-05, 1.20495934e-05,
|
174 |
+
1.25650204e-05, 1.16137307e-05, 1.18198168e-05, 1.15763123e-05,
|
175 |
+
1.24373146e-05, 1.25643137e-05, 1.48531772e-05, 1.28844113e-05,
|
176 |
+
1.19790957e-05, 1.42352001e-05, 2.61451223e-05, 1.16819347e-05],
|
177 |
+
dtype=float32),
|
178 |
+
'vid': '3001_21_JUMP_STREET',
|
179 |
+
'windows': array([[ 0, 128],
|
180 |
+
[ 64, 192],
|
181 |
+
[ 128, 256],
|
182 |
+
...,
|
183 |
+
[32576, 32704],
|
184 |
+
[32640, 32768],
|
185 |
+
[32704, 32832]])}
|
186 |
+
```
|
187 |
+
|